AI (2561 Part Series) 1 Agent Learning via Early Experience 2 MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with HolisticPlatform and Adaptive Hybrid Policy Optimization ... 2557 more parts... 3 MemMamba: Rethinking Memory Patterns in State Space Model 4 UniVideo: Unified Understanding, Generation, and Editing for Videos 5 VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches viaIn-Context Conditioning 6 DreamOmni2: Multimodal Instruction-based Editing and Generation 7 From What to Why: A Multi-Agent System for Evidence-based Chemical ReactionCondition Reasoning 8 Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning 9 When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs 10 Low-probability Tokens Sustain Exploration in Reinforcement Learning withVerifiable Reward 11 The Alignment Waltz: Jointly Training Agents to Collaborate for Safety 12 Training-Free Group Relative Policy Optimization 13 Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense 14 NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents 15 ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction withStructured Scene Representation 16 DeepPrune: Parallel Scaling without Inter-trace Redundancy 17 First Try Matters: Revisiting the Role of Reflection in Reasoning Models 18 LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty fromMisaligned Samples to Biased Human-AI Interaction 19 UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution 20 NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Modelsunder Data Constraints 21 CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards 22 PickStyle: Video-to-Video Style Transfer with Context-Style Adapters 23 UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG 24 InstructX: Towards Unified Visual Editing with MLLM Guidance 25 LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling 26 Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-HorizonTasks 27 Reinforcing Diffusion Models by Direct Group Preference Optimization 28 Taming Text-to-Sounding Video Generation via Advanced Modality Condition andInteraction 29 Entropy Regularizing Activation: Boosting Continuous Control, Large LanguageModels, and Image Classification with Activation as 30 Memory Retrieval and Consolidation in Large Language Models through FunctionTokens 31 Recycling Pretrained Checkpoints: Orthogonal Growth of Mixture-of-Experts forEfficient Large Language Model Pre-Training 32 GCPO: When Contrast Fails, Go Gold 33 UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections 34 OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-BodyLoco-Manipulation and Scene Interaction 35 DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-WiseNeural Dynamics Model 36 A^2Search: Ambiguity-Aware Question Answering with Reinforcement Learning 37 Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs 38 Search-R3: Unifying Reasoning and Embedding Generation in Large Language Models 39 R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation 40 Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models 41 Beyond Outliers: A Study of Optimizers Under Quantization 42 SViM3D: Stable Video Material Diffusion for Single Image 3D Generation 43 GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations 44 Towards Scalable and Consistent 3D Editing 45 Use the Online Network If You Can: Towards Fast and Stable ReinforcementLearning 46 Fidelity-Aware Data Composition for Robust Robot Generalization 47 SciVideoBench: Benchmarking Scientific Video Reasoning in Large MultimodalModels 48 Large Scale Diffusion Distillation via Score-Regularized Continuous-TimeConsistency 49 Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window 50 OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modelingand LLM Alignment 51 Thinking with Camera: A Unified Multimodal Model for Camera-CentricUnderstanding and Generation 52 D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to EmbodiedAI 53 TAG:Tangential Amplifying Guidance for Hallucination-Resistant DiffusionSampling 54 Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs 55 AutoPR: Let's Automate Your Academic Promotion! 56 R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth andDepth? 57 Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels 58 SpaceVista: All-Scale Visual Spatial Reasoning from mm to km 59 StreamingVLM: Real-Time Understanding for Infinite Video Streams 60 Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting 61 ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level EntropyShaping 62 KORMo: Korean Open Reasoning Model for Everyone 63 DISCO: Diversifying Sample Condensation for Efficient Model Evaluation 64 Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out ofDistribution Generalization 65 Progressive Gaussian Transformer with Anisotropy-aware Sampling for OpenVocabulary Occupancy Prediction 66 StatEval: A Comprehensive Benchmark for Large Language Models in Statistics 67 MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark forReasoning-Intensive Multimodal Retrieval 68 PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs 69 BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation viaExecution 70 Which Heads Matter for Reasoning? RL-Guided KV Cache Compression 71 Dyna-Mind: Learning to Simulate from Experience for Better AI Agents 72 ReviewerToo: Should AI Join The Program Committee? A Look At The Future of PeerReview 73 Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic SpeechRecognition 74 Parallel Test-Time Scaling for Latent Reasoning Models 75 Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in SpokenLanguage Models 76 A Goal Without a Plan Is Just a Wish: Efficient and Effective Global PlannerTraining for Long-Horizon Agent Tasks 77 TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control 78 Mitigating Overthinking through Reasoning Shaping 79 Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols 80 GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare 81 Understanding DeepResearch via Reports 82 One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework 83 Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance forSelf-supervised Monocular Depth Estimation 84 Speculative Jacobi-Denoising Decoding for Accelerating AutoregressiveText-to-image Generation 85 Better Together: Leveraging Unpaired Multimodal Data for Stronger UnimodalModels 86 LightReasoner: Can Small Language Models Teach Large Language Models Reasoning? 87 ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall 88 Formalizing Style in Personal Narratives 89 LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology 90 Temporal Prompting Matters: Rethinking Referring Video Object Segmentation 91 ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL 92 Instant4D: 4D Gaussian Splatting in Minutes 93 QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs 94 Diffusion Transformers with Representation Autoencoders 95 OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs 96 Latent Refinement Decoding: Enhancing Diffusion-Based Language Models byRefining Belief States 97 RLFR: Extending Reinforcement Learning for LLMs with Flow Environment 98 Spotlight on Token Perception for Multimodal Reinforcement Learning 99 AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration 100 DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training 101 Making Mathematical Reasoning Adaptive 102 Demystifying Reinforcement Learning in Agentic Reasoning 103 InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models 104 Building a Foundational Guardrail for General Agentic Systems via Synthetic Data 105 ACADREASON: Exploring the Limits of Reasoning Models with Academic ResearchProblems 106 BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions 107 FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark forEvaluating LLMs 108 DocReward: A Document Reward Model for Structuring and Stylizing 109 Don't Just Fine-tune the Agent, Tune the Environment 110 GIR-Bench: Versatile Benchmark for Generating Images with Reasoning 111 AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4DScenes 112 Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning 113 SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models 114 CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images 115 On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in LargeVision-Language Models 116 High-Fidelity Simulated Data Generation for Real-World Zero-Shot RoboticManipulation Learning with Gaussian Splatting 117 Skill-Targeted Adaptive Training 118 ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding 119 PEAR: Phase Entropy Aware Reward for Efficient Reasoning 120 Self-Improving LLM Agents at Test-Time 121 FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging withDiffusion Decoding 122 The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs 123 Stable Video Infinity: Infinite-Length Video Generation with Error Recycling 124 LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Modelsvia Likelihood Preference 125 HUME: Measuring the Human-Model Performance Gap in Text Embedding Task 126 SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and AdaptiveReasoning 127 From Data to Rewards: a Bilevel Optimization Perspective on Maximum LikelihoodEstimation 128 InfiniHuman: Infinite 3D Human Creation with Precise Control 129 LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoning 130 World-To-Image: Grounding Text-to-Image Generation with Agent-Driven WorldKnowledge 131 RePro: Training Language Models to Faithfully Recycle the Web for Pretraining 132 Multimodal Policy Internalization for Conversational Agents 133 Graph Diffusion Transformers are In-Context Molecular Designers 134 VER: Vision Expert Transformer for Robot Learning via Foundation Distillationand Dynamic Routing 135 A Tale of LLMs and Induced Small Proxies: Scalable Agents for Knowledge Mining 136 Are Large Reasoning Models Interruptible? 137 IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment 138 AndesVL Technical Report: An Efficient Mobile-side Multimodal Large LanguageModel 139 ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for LargeVision-and-Language Models 140 The Hidden DNA of LLM-Generated JavaScript: Structural Patterns EnableHigh-Accuracy Authorship Attribution 141 CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biasesin LLMs 142 The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against LlmJailbreaks and Prompt Injections 143 Through the Perspective of LiDAR: A Feature-Enriched and Uncertainty-AwareAnnotation Pipeline for Terrestrial Point Cloud Segmen 144 The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-FormAnswers 145 MultiCOIN: Multi-Modal COntrollable Video INbetweening 146 Pathology-CoT: Learning Visual Chain-of-Thought Agent from Expert Whole SlideImage Diagnosis Behavior 147 Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm EnablesFine-Grained Policy Optimization 148 FlashWorld: High-quality 3D Scene Generation within Seconds 149 CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Modelfor Autonomous Driving 150 InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue 151 Generative Universal Verifier as Multimodal Meta-Reasoner 152 Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully OpenMLLMs 153 Trace Anything: Representing Any Video in 4D via Trajectory Fields 154 ParallelBench: Understanding the Trade-offs of Parallel Decoding in DiffusionLLMs 155 LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models 156 The Role of Computing Resources in Publishing Foundation Model Research 157 UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning 158 Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark 159 FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model 160 PhysMaster: Mastering Physical Representation for Video Generation viaReinforcement Learning 161 Revisiting Model Interpolation for Efficient Reasoning 162 UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE 163 Direct Multi-Token Decoding 164 NOSA: Native and Offloadable Sparse Attention 165 CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in LatentWorld Models for Autonomous Driving 166 Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math 167 MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training 168 HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-AgentCommunication 169 GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-TurnDeep Search 170 InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for GeneralistRobot Policy 171 Deflanderization for Game Dialogue: Balancing Character Authenticity with TaskExecution in LLM-based NPCs 172 Universal Image Restoration Pre-training via Masked Degradation Classification 173 X-VLA: Soft-Prompted Transformer as Scalable Cross-EmbodimentVision-Language-Action Model 174 WithAnyone: Towards Controllable and ID Consistent Image Generation 175 From Pixels to Words -- Towards Native Vision-Language Primitives at Scale 176 Agentic Entropy-Balanced Policy Optimization 177 AI for Service: Proactive Assistance with AI Glasses 178 Information Gain-based Policy Optimization: A Simple and Effective Approach forMulti-Turn LLM Agents 179 PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-CompactVision-Language Model 180 Attention Is All You Need for KV Cache in Diffusion LLMs 181 BitNet Distillation 182 TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar 183 LLM-guided Hierarchical Retrieval 184 Qwen3Guard Technical Report 185 Large Language Models Do NOT Really Know What They Don't Know 186 Learning an Image Editing Model without Image Editing Pairs 187 VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a VideoGenerator 188 pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation 189 MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal MathematicalReasoning 190 Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 TechReport 191 Expertise need not monopolize: Action-Specialized Mixture of Experts forVision-Language-Action Learning 192 MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-AugmentedGeneration Systems 193 RefusalBench: Generative Evaluation of Selective Refusal in Grounded LanguageModels 194 Ponimator: Unfolding Interactive Pose for Versatile Human-human InteractionAnimation 195 Beyond One World: Benchmarking Super Heros in Role-Playing Across MultiversalContexts 196 When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection withPsiloQA 197 ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond SemanticDependency Constraints 198 COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with ThoughtProcesses 199 VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework forUnseen Concept Manipulation 200 Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures 201 LLMs Can Get Brain Rot! 202 LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild 203 Agentic Design of Compositional Machines 204 VLA-0: Building State-of-the-Art VLAs with Zero Modification 205 SimKO: Simple Pass@K Policy Optimization 206 LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training 207 DialectGen: Benchmarking and Improving Dialect Robustness in MultimodalGeneration 208 LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning 209 Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection toDiffusion Language Models 210 RealDPO: Real or Not Real, that is the Preference 211 The German Commons - 154 Billion Tokens of Openly Licensed Text for GermanLanguage Models 212 On Pretraining for Project-Level Code Completion 213 Budget-aware Test-time Scaling via Discriminative Verification 214 FML-bench: A Benchmark for Automatic ML Research Agents Highlighting theImportance of Exploration Breadth 215 Predicting Task Performance with Context-aware Scaling Laws 216 Synthesizing Agentic Data for Web Agents with Progressive Difficulty EnhancementMechanisms 217 AnyUp: Universal Feature Upsampling 218 SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel ViewSynthesis 219 GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling forStep-Level Reasoning 220 Unlocking Out-of-Distribution Generalization in Transformers via RecursiveLatent Space Reasoning 221 RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval AugmentedGeneration Systems 222 Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference 223 LaSeR: Reinforcement Learning with Last-Token Self-Rewarding 224 OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM 225 NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks 226 Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset 227 Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery 228 Latent Diffusion Model without Variational Autoencoder 229 LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal 230 MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning 231 A^2FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning 232 BLIP3o-NEXT: Next Frontier of Native Image Generation 233 Language Models Model Language 234 InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-BasedIncremental Training 235 Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation 236 Explore to Evolve: Scaling Evolved Aggregation Logic via Proactive OnlineExploration for Deep Research Agents 237 Foundation Models for Scientific Discovery: From Paradigm Enhancement toParadigm Transition 238 VISTA: A Test-Time Self-Improving Video Generation Agent 239 DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token viaReinforcement Learning 240 Emergent Misalignment via In-Context Learning: Narrow in-context examples canproduce broadly misaligned LLMs 241 Build Your Personalized Research Group: A Multiagent Framework for Continual andInteractive Science Automation 242 FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in FinanceDomain 243 Robust Layerwise Scaling Rules by Proper Weight Decay Tuning 244 Rewiring Experts on the Fly:Continuous Rerouting for Better Online Adaptation inMixture-of-Expert models 245 Paper2Web: Let's Make Your Paper Alive! 246 Train a Unified Multimodal Data Quality Classifier with Synthetic Data 247 PICABench: How Far Are We from Physically Realistic Image Editing? 248 DeepAnalyze: Agentic Large Language Models for Autonomous Data Science 249 Glyph: Scaling Context Windows via Visual-Text Compression 250 Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation 251 When to Ensemble: Identifying Token-Level Points for Stable and Fast LLMEnsembling 252 FineVision: Open Data Is All You Need 253 QueST: Incentivizing LLMs to Generate Difficult Problems 254 Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling 255 RL makes MLLMs see better than SFT 256 Annotation-Efficient Universal Honesty Alignment 257 Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuningand MLLM Implicit Feedback 258 ConsistEdit: Highly Consistent and Precise Training-free Visual Editing 259 Executable Knowledge Graphs for Replicating AI Research 260 Deep Self-Evolving Reasoning 261 Chronos-2: From Univariate to Universal Forecasting 262 Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI 263 Constantly Improving Image Models Need Constantly Improving Benchmarks 264 Enterprise Deep Research: Steerable Multi-Agent Deep Research for EnterpriseAnalytics 265 UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action 266 Agentic Reinforcement Learning for Search is Unsafe 267 Distractor Injection Attacks on Large Reasoning Models: Characterization andDefense 268 Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset 269 Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval andFiltering 270 Foundational Automatic Evaluators: Scaling Multi-Task Generative EvaluatorTraining for Reasoning-Centric Domains 271 MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision andLanguage Models 272 Balanced Multi-Task Attention for Satellite Image Classification: A SystematicApproach to Achieving 97.23% Accuracy on EuroSAT W 273 Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in LargeLanguage Models 274 Automated Composition of Agents: A Knapsack Approach for Agentic ComponentSelection 275 AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning 276 On Non-interactive Evaluation of Animal Communication Translators 277 GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer 278 Test-Time Scaling of Reasoning Models for Machine Translation 279 What Limits Agentic Systems Efficiency? 280 LightMem: Lightweight and Efficient Memory-Augmented Generation 281 World-in-World: World Models in a Closed-Loop World 282 UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-ImageGeneration 283 Chem-R: Learning to Reason as a Chemist 284 MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation 285 Grasp Any Region: Towards Precise, Contextual Pixel Understanding for MultimodalLLMs 286 IF-VidCap: Can Video Caption Models Follow Instructions? 287 MT-Video-Bench: A Holistic Video Understanding Benchmark for EvaluatingMultimodal LLMs in Multi-Turn Dialogues 288 ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning 289 ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder 290 MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models 291 DSI-Bench: A Benchmark for Dynamic Spatial Intelligence 292 UltraGen: High-Resolution Video Generation with Hierarchical Attention 293 Video Reasoning without Training 294 Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposureMonocular Videos 295 PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies 296 AlphaQuanter: An End-to-End Tool-Orchestrated Agentic Reinforcement LearningFramework for Stock Trading 297 Extracting alignment data in open models 298 EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning 299 Efficient Long-context Language Model Training by Core Attention Disaggregation 300 GAS: Improving Discretization of Diffusion ODEs via Generalized AdversarialSolver 301 Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-TranslationSolution 302 DeepSeek-OCR: Contexts Optical Compression 303 Think with 3D: Geometric Imagination Grounded Spatial Reasoning from LimitedViews 304 Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth 305 Expanding the Action Space of LLMs to Reason Beyond Language 306 Planned Diffusion 307 Unimedvl: Unifying Medical Multimodal Understanding And Generation ThroughObservation-Knowledge-Analysis 308 Predicting the Unpredictable: Reproducible BiLSTM Forecasting of Incident Countsin the Global Terrorism Database (GTD) 309 Static Sandboxes Are Inadequate: Modeling Societal Complexity RequiresOpen-Ended Co-Evolution in LLM-Based Multi-Agent Simulatio 310 PokeeResearch: Effective Deep Research via Reinforcement Learning from AIFeedback and Robust Reasoning Scaffold 311 Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration 312 When Correct Is Not Safe: Can We Trust Functionally Correct Patches Generatedby Code Agents? 313 LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts 314 Every Attention Matters: An Efficient Hybrid Architecture for Long-ContextReasoning 315 BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced PolicyOptimization with Adaptive Clipping 316 DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile PhoneAgents 317 GigaBrain-0: A World Model-Powered Vision-Language-Action Model 318 ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases 319 Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1 320 Towards Faithful and Controllable Personalization via Critique-Post-EditReinforcement Learning 321 VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos 322 Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing 323 Language Models are Injective and Hence Invertible 324 Attention Sinks in Diffusion Language Models 325 Unified Reinforcement and Imitation Learning for Vision-Language Models 326 olmOCR 2: Unit Test Rewards for Document OCR 327 Decomposed Attention Fusion in MLLMs for Training-Free Video ReasoningSegmentation 328 FinSight: Towards Real-World Financial Deep Research 329 Directional Reasoning Injection for Fine-Tuning MLLMs 330 KORE: Enhancing Knowledge Injection for Large Multimodal Models viaKnowledge-Oriented Augmentations and Constraints 331 Are they lovers or friends? Evaluating LLMs' Social Reasoning in English andKorean Dialogues 332 OmniNWM: Omniscient Driving Navigation World Models 333 ColorAgent: Building A Robust, Personalized, and Interactive OS Agent 334 TheMCPCompany: Creating General-purpose Agents with Task-specific Tools 335 NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning 336 From Charts to Code: A Hierarchical Benchmark for Multimodal Models 337 MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for LargeMultimodal Models 338 Steering Autoregressive Music Generation with Recursive Feature Machines 339 ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer andJudge 340 Learning from the Best, Differently: A Diversity-Driven Rethinking on DataSelection 341 When Do Transformers Learn Heuristics for Graph Connectivity? 342 See the Text: From Tokenization to Visual Reading 343 RIR-Mega: a large-scale simulated room impulse response dataset for machinelearning and room acoustics modeling 344 What Questions Should Robots Be Able to Answer? A Dataset of User Questions forExplainable Robotics 345 DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation inText-to-Image Models 346 Machine Text Detectors are Membership Inference Attacks 347 SAVANT: Semantic Analysis with Vision-Augmented Anomaly deTection 348 Accelerating Vision Transformers with Adaptive Patch Sizes 349 Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs inMultimodal LLMs 350 DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking 351 HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents inHierarchical Rule Application 352 Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall 353 Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence 354 Every Question Has Its Own Value: Reinforcement Learning with Explicit HumanValues 355 HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives 356 LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas 357 AlphaFlow: Understanding and Improving MeanFlow Models 358 ARGenSeg: Image Segmentation with Autoregressive Image Generation Model 359 Conan: Progressive Learning to Reason Like a Detective over Multi-Scale VisualEvidence 360 The Massive Legal Embedding Benchmark (MLEB) 361 AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders 362 DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion 363 Search Self-play: Pushing the Frontier of Agent Capability without Supervision 364 Emergence of Linear Truth Encodings in Language Models 365 From Masks to Worlds: A Hitchhiker's Guide to World Models 366 Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets 367 Thought Communication in Multiagent Collaboration 368 AlphaOPT: Formulating Optimization Programs with Self-Improving LLM ExperienceLibrary 369 SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-LanguageModels 370 Investigating Safety Vulnerabilities of Large Audio-Language Models UnderSpeaker Emotional Variations 371 Diff-XYZ: A Benchmark for Evaluating Diff Understanding 372 CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-AugmentedValidation 373 Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs 374 Communication to Completion: Modeling Collaborative Workflows with IntelligentMulti-Agent Communication 375 Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference 376 Long-Context Attention Benchmark: From Kernel Efficiency to Distributed ContextParallelism 377 ComProScanner: A multi-agent based framework for composition-property structureddata extraction from scientific literature 378 MSC-Bench: A Rigorous Benchmark for Multi-Server Tool Orchestration 379 DeepAgent: A General Reasoning Agent with Scalable Toolsets 380 Video-As-Prompt: Unified Semantic Control for Video Generation 381 UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning 382 Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation 383 A Definition of AGI 384 From Denoising to Refining: A Corrective Framework for Vision-Language DiffusionModel 385 Sparser Block-Sparse Attention via Token Permutation 386 RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation viaHierarchical Model Merging 387 Reasoning with Sampling: Your Base Model is Smarter Than You Think 388 Model Merging with Functional Dual Anchors 389 Attention Is All You Need 390 RoBERTa: A Robustly Optimized BERT Pretraining Approach 391 YOLOv3: An Incremental Improvement 392 MobileNets: Efficient Convolutional Neural Networks for Mobile VisionApplications 393 Proximal Policy Optimization Algorithms 394 Distilling the Knowledge in a Neural Network 395 LLaMA: Open and Efficient Foundation Language Models 396 YOLOv4: Optimal Speed and Accuracy of Object Detection 397 Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling 398 Playing Atari with Deep Reinforcement Learning 399 Representation Learning with Contrastive Predictive Coding 400 Layer Normalization 401 TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems 402 Community detection in graphs 403 Conditional Generative Adversarial Nets 404 UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction 405 Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine LearningAlgorithms 406 Rethinking Atrous Convolution for Semantic Image Segmentation 407 DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter 408 SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB modelsize 409 Hierarchical Text-Conditional Image Generation with CLIP Latents 410 Improving neural networks by preventing co-adaptation of feature detectors 411 Evaluating Large Language Models Trained on Code 412 Google's Neural Machine Translation System: Bridging the Gap between Human andMachine Translation 413 ADADELTA: An Adaptive Learning Rate Method 414 UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild 415 Training Verifiers to Solve Math Word Problems 416 Scaling Laws for Neural Language Models 417 Attention U-Net: Learning Where to Look for the Pancreas 418 ShapeNet: An Information-Rich 3D Model Repository 419 Evaluation: from precision, recall and F-measure to ROC, informedness,markedness and correlation 420 An Empirical Evaluation of Generic Convolutional and Recurrent Networks forSequence Modeling 421 On the Opportunities and Risks of Foundation Models 422 OpenAI Gym 423 Variational Inference: A Review for Statisticians 424 A Quantitative Measure Of Fairness And Discrimination For Resource Allocation InShared Computer Systems 425 YOLOX: Exceeding YOLO Series in 2021 426 Federated Learning: Strategies for Improving Communication Efficiency 427 Wasserstein GAN 428 Classifier-Free Diffusion Guidance 429 Fast Graph Representation Learning with PyTorch Geometric 430 CoSaMP: Iterative signal recovery from incomplete and inaccurate samples 431 DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via ReinforcementLearning 432 Longformer: The Long-Document Transformer 433 TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation 434 End to End Learning for Self-Driving Cars 435 Bidirectional LSTM-CRF Models for Sequence Tagging 436 OPT: Open Pre-trained Transformer Language Models 437 Generating Sequences With Recurrent Neural Networks 438 The Kinetics Human Action Video Dataset 439 Improved Regularization of Convolutional Neural Networks with Cutout 440 Variational Graph Auto-Encoders 441 Instance Normalization: The Missing Ingredient for Fast Stylization 442 The information bottleneck method 443 Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour 444 Improved Baselines with Momentum Contrastive Learning 445 Sparks of Artificial General Intelligence: Early experiments with GPT-4 446 A Survey of Large Language Models 447 Deep Learning using Rectified Linear Units (ReLU) 448 Objects as Points 449 Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge 450 Estimating or Propagating Gradients Through Stochastic Neurons for ConditionalComputation 451 In Defense of the Triplet Loss for Person Re-Identification 452 Relational inductive biases, deep learning, and graph networks 453 Training a Helpful and Harmless Assistant with Reinforcement Learning from HumanFeedback 454 MMDetection: Open MMLab Detection Toolbox and Benchmark 455 DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open LanguageModels 456 Empirical Evaluation of Rectified Activations in Convolutional Network 457 Past, Present, and Future of Simultaneous Localization And Mapping: Towards theRobust-Perception Age 458 An Overview of Multi-Task Learning in Deep Neural Networks 459 On discrete cosine transform 460 A Neural Algorithm of Artistic Style 461 The Effectiveness of Data Augmentation in Image Classification using DeepLearning 462 CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with DeepLearning 463 HuggingFace's Transformers: State-of-the-art Natural Language Processing 464 Recurrent Neural Network Regularization 465 Federated Learning with Non-IID Data 466 Mistral 7B 467 Gemini 1.5: Unlocking multimodal understanding across millions of tokens ofcontext 468 Link Prediction in Complex Networks: A Survey 469 Soft Actor-Critic Algorithms and Applications 470 Microsoft COCO Captions: Data Collection and Evaluation Server 471 BLOOM: A 176B-Parameter Open-Access Multilingual Language Model 472 Concrete Problems in AI Safety 473 Program Synthesis with Large Language Models 474 Progressive Neural Networks 475 A Tutorial on Principal Component Analysis 476 Counterfactual Explanations without Opening the Black Box: Automated Decisionsand the GDPR 477 Code Llama: Open Foundation Models for Code 478 Fine-Grained Visual Classification of Aircraft 479 Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at AnyResolution 480 Qwen2.5 Technical Report 481 Retrieval-Augmented Generation for Large Language Models: A Survey 482 A Tutorial on Bayesian Optimization of Expensive Cost Functions, withApplication to Active User Modeling and Hierarchical Reinfo 483 YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications 484 A Critical Review of Recurrent Neural Networks for Sequence Learning 485 LSUN: Construction of a Large-scale Image Dataset using Deep Learning withHumans in the Loop 486 Training Compute-Optimal Large Language Models 487 Invariant Risk Minimization 488 The Pile: An 800GB Dataset of Diverse Text for Language Modeling 489 Iterative Hard Thresholding for Compressed Sensing 490 Neural Turing Machines 491 Decoupled Weight Decay Regularization 492 On First-Order Meta-Learning Algorithms 493 SmoothGrad: removing noise by adding noise 494 Theano: A Python framework for fast computation of mathematical expressions 495 Adversarial Autoencoders 496 GPT-4o System Card 497 Deep Learning for Medical Image Analysis 498 MXNet: A Flexible and Efficient Machine Learning Library for HeterogeneousDistributed Systems 499 Megatron-LM: Training Multi-Billion Parameter Language Models Using ModelParallelism 500 Offline Reinforcement Learning: Tutorial, Review, and Perspectives on OpenProblems 501 ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation 502 Deep Speech: Scaling up end-to-end speech recognition 503 DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with LowBitwidth Gradients 504 Generating Long Sequences with Sparse Transformers 505 VisualBERT: A Simple and Performant Baseline for Vision and Language 506 Constitutional AI: Harmlessness from AI Feedback 507 Learning Face Representation from Scratch 508 Fine-Tuning Language Models from Human Preferences 509 Universal and Transferable Adversarial Attacks on Aligned Language Models 510 Qwen2.5-VL Technical Report 511 Federated Optimization: Distributed Machine Learning for On-Device Intelligence 512 Beyond the Imitation Game: Quantifying and extrapolating the capabilities oflanguage models 513 A Tutorial on Bayesian Optimization 514 Binarized Neural Networks 515 Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning 516 Smart Radio Environments Empowered by Reconfigurable Intelligent Surfaces: Howit Works, State of Research, and Road Ahead 517 DSSD : Deconvolutional Single Shot Detector 518 Weight Uncertainty in Neural Networks 519 Sequence Transduction with Recurrent Neural Networks 520 BERTopic: Neural topic modeling with a class-based TF-IDF procedure 521 Linformer: Self-Attention with Linear Complexity 522 Dota 2 with Large Scale Deep Reinforcement Learning 523 Artificial Intelligence: the global landscape of ethics guidelines 524 BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain 525 MOT16: A Benchmark for Multi-Object Tracking 526 IPFS - Content Addressed, Versioned, P2P File System 527 Community detection in networks: A user guide 528 Mastering Chess and Shogi by Self-Play with a General Reinforcement LearningAlgorithm 529 Understanding Neural Networks Through Deep Visualization 530 cuDNN: Efficient Primitives for Deep Learning 531 Tutorial on Variational Autoencoders 532 AutoAugment: Learning Augmentation Policies from Data 533 Multitask Prompted Training Enables Zero-Shot Task Generalization 534 Open3D: A Modern Library for 3D Data Processing 535 Highway Networks 536 Transferability in Machine Learning: from Phenomena to Black-Box Attacks usingAdversarial Samples 537 Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation,Progression Assessment, and Overall Survival Predi 538 A Neural Conversational Model 539 NIPS 2016 Tutorial: Generative Adversarial Networks 540 Imagen Video: High Definition Video Generation with Diffusion Models 541 LaMDA: Language Models for Dialog Applications 542 Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone 543 Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets 544 Deep Reinforcement Learning: An Overview 545 Deep learning in remote sensing: a review 546 word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embeddingmethod 547 Federated Learning for Mobile Keyboard Prediction 548 LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs 549 Deep Convolutional Networks on Graph-Structured Data 550 Deep Learning for Anomaly Detection: A Survey 551 Evolution Strategies as a Scalable Alternative to Reinforcement Learning 552 Exploiting Similarities among Languages for Machine Translation 553 MediaPipe: A Framework for Building Perception Pipelines 554 A guide to convolution arithmetic for deep learning 555 Coase's Penguin, or Linux and the Nature of the Firm 556 CatBoost: gradient boosting with categorical features support 557 Consistent Individualized Feature Attribution for Tree Ensembles 558 LEAF: A Benchmark for Federated Settings 559 Qwen3 Technical Report 560 Pitfalls of Graph Neural Network Evaluation 561 D4RL: Datasets for Deep Data-Driven Reinforcement Learning 562 WebGPT: Browser-assisted question-answering with human feedback 563 Qwen2 Technical Report 564 Opening the Black Box of Deep Neural Networks via Information 565 No Language Left Behind: Scaling Human-Centered Machine Translation 566 The CMA Evolution Strategy: A Tutorial 567 MUSAN: A Music, Speech, and Noise Corpus 568 Scaling Language Models: Methods, Analysis & Insights from Training Gopher 569 Mixtral of Experts 570 Differentially Private Federated Learning: A Client Level Perspective 571 The Roadmap to 6G -- AI Empowered Wireless Networks 572 Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by theInternational Skin Imaging Collaboration (ISIC) 573 Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models 574 A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT 575 Theano: new features and speed improvements 576 Distributionally Robust Neural Networks for Group Shifts: On the Importance ofRegularization for Worst-Case Generalization 577 Improved Simulation of Stabilizer Circuits 578 Gemma 2: Improving Open Language Models at a Practical Size 579 The 2017 DAVIS Challenge on Video Object Segmentation 580 Blockchain Technology Overview 581 Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition 582 DeepID3: Face Recognition with Very Deep Neural Networks 583 ERNIE: Enhanced Representation through Knowledge Integration 584 Expanding Performance Boundaries of Open-Source Multimodal Models with Model,Data, and Test-Time Scaling 585 Resnet in Resnet: Generalizing Residual Architectures 586 Towards Accurate Generative Models of Video: A New Metric & Challenges 587 The History Began from AlexNet: A Comprehensive Survey on Deep LearningApproaches 588 Joint 2D-3D-Semantic Data for Indoor Scene Understanding 589 An O(m) Algorithm for Cores Decomposition of Networks 590 eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers 591 Compressed Sensing with Coherent and Redundant Dictionaries 592 Deep Graph Contrastive Representation Learning 593 On Evaluating Adversarial Robustness 594 TUDataset: A collection of benchmark datasets for learning with graphs 595 Detecting Adversarial Samples from Artifacts 596 Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient DeepArchitectures 597 A General Language Assistant as a Laboratory for Alignment 598 A large annotated medical image dataset for the development and evaluation ofsegmentation algorithms 599 StarCraft II: A New Challenge for Reinforcement Learning 600 fastMRI: An Open Dataset and Benchmarks for Accelerated MRI 601 Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning 602 A Generalization of Transformer Networks to Graphs 603 Hybrid Beamforming for Massive MIMO - A Survey 604 FourCastNet: A Global Data-driven High-resolution Weather Model using AdaptiveFourier Neural Operators 605 LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention 606 Galactica: A Large Language Model for Science 607 Text Embeddings by Weakly-Supervised Contrastive Pre-training 608 Model-Agnostic Interpretability of Machine Learning 609 Show Your Work: Scratchpads for Intermediate Computation with Language Models 610 A Comprehensive Survey of Data Mining-based Fraud Detection Research 611 COVID-CT-Dataset: A CT Scan Dataset about COVID-19 612 Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving 613 iBOT: Image BERT Pre-Training with Online Tokenizer 614 Understanding disentangling in $β$-VAE 615 On Evaluation of Embodied Navigation Agents 616 AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, andMitigating Unwanted Algorithmic Bias 617 Jukebox: A Generative Model for Music 618 SpeechBrain: A General-Purpose Speech Toolkit 619 Unity: A General Platform for Intelligent Agents 620 Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs 621 VisDA: The Visual Domain Adaptation Challenge 622 Snips Voice Platform: an embedded Spoken Language Understanding system forprivate-by-design voice interfaces 623 Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, LongContext, and Next Generation Agentic Capabilities 624 word2vec Parameter Learning Explained 625 MediaPipe Hands: On-device Real-time Hand Tracking 626 Role-Based Access Controls 627 Deep Learning Scaling is Predictable, Empirically 628 BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View 629 Carbon Emissions and Large Neural Network Training 630 MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking 631 High-Resolution Representations for Labeling Pixels and Regions 632 Not Just a Black Box: Learning Important Features Through Propagating ActivationDifferences 633 Survey of Security and Privacy Issues of Internet of Things 634 Deterministic Designs with Deterministic Guarantees: Toeplitz Compressed SensingMatrices, Sequence Designs and System Identifica 635 DAPO: An Open-Source LLM Reinforcement Learning System at Scale 636 FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation 637 graph2vec: Learning Distributed Representations of Graphs 638 The State of Sparsity in Deep Neural Networks 639 Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic: InitialResults for Automated Detection & Patient Monitoring 640 DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts LanguageModel 641 Deep Learning Recommendation Model for Personalization and RecommendationSystems 642 From Local to Global: A Graph RAG Approach to Query-Focused Summarization 643 Julia: A Fast Dynamic Language for Technical Computing 644 Quantifying the Carbon Emissions of Machine Learning 645 SIoU Loss: More Powerful Learning for Bounding Box Regression 646 The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation andRadiogenomic Classification 647 Metrics for Explainable AI: Challenges and Prospects 648 Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph NeuralNetworks 649 Split learning for health: Distributed deep learning without sharing raw patientdata 650 Temporal Graph Networks for Deep Learning on Dynamic Graphs 651 Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-ScaleGenerative Language Model 652 Population Based Training of Neural Networks 653 Bayesian Convolutional Neural Networks with Bernoulli Approximate VariationalInference 654 Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks 655 MiniCPM-V: A GPT-4V Level MLLM on Your Phone 656 The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) 657 CrowdHuman: A Benchmark for Detecting Human in a Crowd 658 Mastering Diverse Domains through World Models 659 Illuminating search spaces by mapping elites 660 Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic 661 A Gentle Introduction to Conformal Prediction and Distribution-Free UncertaintyQuantification 662 The Malicious Use of Artificial Intelligence: Forecasting, Prevention, andMitigation 663 Federated Optimization:Distributed Optimization Beyond the Datacenter 664 Stable Architectures for Deep Neural Networks 665 What do we need to build explainable AI systems for the medical domain? 666 Deep Learning for Classical Japanese Literature 667 On a Formal Model of Safe and Scalable Self-driving Cars 668 FinBERT: Financial Sentiment Analysis with Pre-trained Language Models 669 LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale 670 AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data 671 Interpretable classifiers using rules and Bayesian analysis: Building a betterstroke prediction model 672 An Overview on Clustering Methods 673 On Quantum Cellular Automata 674 Gemma: Open Models Based on Gemini Research and Technology 675 ClipCap: CLIP Prefix for Image Captioning 676 MOT20: A benchmark for multi object tracking in crowded scenes 677 Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark 678 A Note on the Inception Score 679 Mining Educational Data to Analyze Students' Performance 680 Skin Lesion Analysis toward Melanoma Detection: A Challenge at the InternationalSymposium on Biomedical Imaging (ISBI) 2016, hos 681 Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error LinearUnits 682 Text mining and visualization using VOSviewer 683 $π_0$: A Vision-Language-Action Flow Model for General Robot Control 684 iDLG: Improved Deep Leakage from Gradients 685 Reinforcement Learning and Control as Probabilistic Inference: Tutorial andReview 686 VideoChat: Chat-Centric Video Understanding 687 Cloud Programming Simplified: A Berkeley View on Serverless Computing 688 From Big to Small: Multi-Scale Local Planar Guidance for Monocular DepthEstimation 689 Theory of Rumour Spreading in Complex Social Networks 690 Modern hierarchical, agglomerative clustering algorithms 691 Behavior Regularized Offline Reinforcement Learning 692 On the (Statistical) Detection of Adversarial Examples 693 A Simple Way to Initialize Recurrent Networks of Rectified Linear Units 694 A Survey of Neuromorphic Computing and Neural Networks in Hardware 695 The Power Grid as a Complex Network: a Survey 696 Roulette-wheel selection via stochastic acceptance 697 EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning 698 Dissipation of stop-and-go waves via control of autonomous vehicles: Fieldexperiments 699 Understanding Modern Banking Ledgers through Blockchain Technologies: Future ofTransaction Processing and Smart Contracts on the 700 ReMixMatch: Semi-Supervised Learning with Distribution Alignment andAugmentation Anchoring 701 How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, andDetection 702 Release Strategies and the Social Impacts of Language Models 703 Equivalence of distance-based and RKHS-based statistics in hypothesis testing 704 Yi: Open Foundation Models by 01.AI 705 Interval Neutrosophic Sets and Logic: Theory and Applications in Computing 706 Instruction Tuning for Large Language Models: A Survey 707 Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models 708 Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative forTraining Deep Neural Networks for Reinforcement Learnin 709 Learning Spatial Fusion for Single-Shot Object Detection 710 Large-scale Simple Question Answering with Memory Networks 711 Massive MIMO is a Reality -- What is Next? Five Promising Research Directionsfor Antenna Arrays 712 Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problemswith Sparse Rewards 713 A Survey on LLM-as-a-Judge 714 Mish: A Self Regularized Non-Monotonic Activation Function 715 Adversarial Attacks and Defences: A Survey 716 Instruction Tuning with GPT-4 717 Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks 718 Revisiting Small Batch Training for Deep Neural Networks 719 Spanish Pre-trained BERT Model and Evaluation Data 720 Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism 721 Semi-Supervised Learning with Generative Adversarial Networks 722 A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets 723 Detect overlapping and hierarchical community structure in networks 724 WorldSimBench: Towards Video Generation Models as World Simulators 725 Clustering and Community Detection in Directed Networks: A Survey 726 BlazePose: On-device Real-time Body Pose tracking 727 Qwen2.5-Coder Technical Report 728 ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth 729 KG-BERT: BERT for Knowledge Graph Completion 730 Multi-Task Learning with Deep Neural Networks: A Survey 731 An evaluation of Naive Bayesian anti-spam filtering 732 A Survey on Metric Learning for Feature Vectors and Structured Data 733 Agile Software Development Methods: Review and Analysis 734 Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-LanguageTasks 735 BinaryNet: Training Deep Neural Networks with Weights and ActivationsConstrained to +1 or -1 736 DeepFakes: a New Threat to Face Recognition? Assessment and Detection 737 What makes ImageNet good for transfer learning? 738 AWAC: Accelerating Online Reinforcement Learning with Offline Datasets 739 Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders 740 Rhythms of social interaction: messaging within a massive online network 741 CodeBLEU: a Method for Automatic Evaluation of Code Synthesis 742 MONAI: An open-source framework for deep learning in healthcare 743 Deep Ensembles: A Loss Landscape Perspective 744 A Comprehensive Survey of AI-Generated Content (AIGC): A History of GenerativeAI from GAN to ChatGPT 745 EVA-CLIP: Improved Training Techniques for CLIP at Scale 746 A White Paper on Neural Network Quantization 747 LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model 748 Large Language Models: A Survey 749 Universal Differential Equations for Scientific Machine Learning 750 Opportunities and Challenges in Explainable Artificial Intelligence (XAI): ASurvey 751 ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate 752 Rotation-invariant convolutional neural networks for galaxy morphologyprediction 753 Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations 754 Communication-Efficient On-Device Machine Learning: Federated Distillation andAugmentation under Non-IID Private Data 755 Recent Advances in Recurrent Neural Networks 756 Adaptive simulated annealing (ASA): Lessons learned 757 Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS 758 A Brief Review of Nature-Inspired Algorithms for Optimization 759 Invertible Conditional GANs for image editing 760 Applied Federated Learning: Improving Google Keyboard Query Suggestions 761 TransTrack: Multiple Object Tracking with Transformer 762 In-context Learning and Induction Heads 763 When Will AI Exceed Human Performance? Evidence from AI Experts 764 The Natural Language Decathlon: Multitask Learning as Question Answering 765 BoT-SORT: Robust Associations Multi-Pedestrian Tracking 766 Detecting Cancer Metastases on Gigapixel Pathology Images 767 Advantage-Weighted Regression: Simple and Scalable Off-Policy ReinforcementLearning 768 Think Locally, Act Globally: Federated Learning with Local and GlobalRepresentations 769 Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, andEarly Stopping 770 Asynchronous Federated Optimization 771 Casper the Friendly Finality Gadget 772 Can You Really Backdoor Federated Learning? 773 Improving Federated Learning Personalization via Model Agnostic Meta Learning 774 Guidelines for including grey literature and conducting multivocal literaturereviews in software engineering 775 Global Attention Mechanism: Retain Information to Enhance Channel-SpatialInteractions 776 Topology optimization based on moving deformable components: A new computationalframework 777 Representation Engineering: A Top-Down Approach to AI Transparency 778 Solving ill-posed inverse problems using iterative deep neural networks 779 Internet of Things: An Overview 780 A Quantum Algorithm for Finding the Minimum 781 Towards General Text Embeddings with Multi-stage Contrastive Learning 782 FedML: A Research Library and Benchmark for Federated Machine Learning 783 Non-Fungible Token (NFT): Overview, Evaluation, Opportunities and Challenges 784 Scalable Tensor Factorizations for Incomplete Data 785 Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: ASpatio-Temporal Deep Learning Approach 786 A Comprehensive Survey on Pretrained Foundation Models: A History from BERT toChatGPT 787 Personalized Federated Learning: A Meta-Learning Approach 788 Kimi k1.5: Scaling Reinforcement Learning with LLMs 789 Random walks and diffusion on networks 790 Qwen2.5-Math Technical Report: Toward Mathematical Expert Model viaSelf-Improvement 791 OCNet: Object Context Network for Scene Parsing 792 Learning Confidence for Out-of-Distribution Detection in Neural Networks 793 Adaptive Personalized Federated Learning 794 Economic-based Distributed Resource Management and Scheduling for Grid Computing 795 Three Approaches for Personalization with Applications to Federated Learning 796 Achieving Human Parity on Automatic Chinese to English News Translation 797 Land Use Classification in Remote Sensing Images by Convolutional NeuralNetworks 798 An Empirical Evaluation of Deep Learning on Highway Driving 799 Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent NeuralNetworks 800 Survey of Nearest Neighbor Techniques 801 Tortured phrases: A dubious writing style emerging in science. Evidence ofcritical issues affecting established journals 802 Hyper-Parameter Optimization: A Review of Algorithms and Applications 803 Improving alignment of dialogue agents via targeted human judgements 804 Towards Out-Of-Distribution Generalization: A Survey 805 VideoGPT: Video Generation using VQ-VAE and Transformers 806 Linear models and linear mixed effects models in R with linguistic applications 807 Accelerating Large Language Model Decoding with Speculative Sampling 808 YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark 809 Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Requestfor Research 810 Real-Time Flying Object Detection with YOLOv8 811 Adaptive Computation Time for Recurrent Neural Networks 812 DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMOApplications 813 Latent Consistency Models: Synthesizing High-Resolution Images with Few-StepInference 814 Online Continual Learning with Maximally Interfered Retrieval 815 Axial Attention in Multidimensional Transformers 816 Challenges of Real-World Reinforcement Learning 817 Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, andLessons Learned 818 Fast Transformer Decoding: One Write-Head is All You Need 819 Multi-Scale Convolutional Neural Networks for Time Series Classification 820 On the Effectiveness of Interval Bound Propagation for Training VerifiablyRobust Models 821 Understanding Neural Networks through Representation Erasure 822 Metamorphic Testing: A New Approach for Generating Next Test Cases 823 Physics-guided Neural Networks (PGNN): An Application in Lake TemperatureModeling 824 Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models 825 Overview of the TREC 2019 deep learning track 826 RTMDet: An Empirical Study of Designing Real-Time Object Detectors 827 Gemma 3 Technical Report 828 Flower Pollination Algorithm: A Novel Approach for Multiobjective Optimization 829 Deep Learning is Robust to Massive Label Noise 830 Achieving Human Parity in Conversational Speech Recognition 831 Lung Infection Quantification of COVID-19 in CT Images with Deep Learning 832 Sentiment Analysis of Twitter Data: A Survey of Techniques 833 An Introductory Study on Time Series Modeling and Forecasting 834 Efficient GAN-Based Anomaly Detection 835 DeepViT: Towards Deeper Vision Transformer 836 On Loss Functions for Deep Neural Networks in Classification 837 A Survey of Attacks, Security Mechanisms and Challenges in Wireless SensorNetworks 838 DeepSeek-VL: Towards Real-World Vision-Language Understanding 839 A study of the effect of JPG compression on adversarial images 840 A Systematic Survey of Prompt Engineering in Large Language Models: Techniquesand Applications 841 TabTransformer: Tabular Data Modeling Using Contextual Embeddings 842 MusicLM: Generating Music From Text 843 The Space of Transferable Adversarial Examples 844 On the Robustness of Interpretability Methods 845 A Short Note about Kinetics-600 846 Learning to Execute 847 Mitigating Sybils in Federated Learning Poisoning 848 On Using Monolingual Corpora in Neural Machine Translation 849 Private federated learning on vertically partitioned data via entity resolutionand additively homomorphic encryption 850 Neural Machine Translation in Linear Time 851 COCO-Text: Dataset and Benchmark for Text Detection and Recognition in NaturalImages 852 The Deepfake Detection Challenge (DFDC) Preview Dataset 853 Ignore Previous Prompt: Attack Techniques For Language Models 854 Retrospective: Flipping Bits in Memory Without Accessing Them: An ExperimentalStudy of DRAM Disturbance Errors 855 The Falcon Series of Open Language Models 856 Is Quantum Bit Commitment Really Possible? 857 Hashing for Similarity Search: A Survey 858 Adding Gradient Noise Improves Learning for Very Deep Networks 859 Practical Secure Aggregation for Federated Learning on User-Held Data 860 Sub-Image Anomaly Detection with Deep Pyramid Correspondences 861 Class Imbalance Problem in Data Mining Review 862 InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-SourceMultimodal Models 863 Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study 864 AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction inStructure-based Drug Discovery 865 Text Understanding from Scratch 866 CloudSim: A Novel Framework for Modeling and Simulation of Cloud ComputingInfrastructures and Services 867 MONet: Unsupervised Scene Decomposition and Representation 868 Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives 869 DeepSeek LLM: Scaling Open-Source Language Models with Longtermism 870 Understanding the exploding gradient problem 871 On the eigenvector bias of Fourier feature networks: From regression to solvingmulti-scale PDEs with physics-informed neural net 872 A Brief Survey of Text Mining: Classification, Clustering and ExtractionTechniques 873 ModelScope Text-to-Video Technical Report 874 HunyuanVideo: A Systematic Framework For Large Video Generative Models 875 C-RNN-GAN: Continuous recurrent neural networks with adversarial training 876 Objective-Reinforced Generative Adversarial Networks (ORGAN) for SequenceGeneration Models 877 Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-ScaleAudio-Language Models 878 A kernel method for canonical correlation analysis 879 Improving Generalization Performance by Switching from Adam to SGD 880 How To Break Anonymity of the Netflix Prize Dataset 881 Neural Processes 882 Differentially Private Generative Adversarial Network 883 Med3D: Transfer Learning for 3D Medical Image Analysis 884 ResNet strikes back: An improved training procedure in timm 885 Geometric GAN 886 FSSD: Feature Fusion Single Shot Multibox Detector 887 R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection 888 Quaternion kinematics for the error-state Kalman filter 889 MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis inOnline Opinion Videos 890 Towards the Systematic Reporting of the Energy and Carbon Footprints of MachineLearning 891 The GAP Benchmark Suite 892 Chameleon: Mixed-Modal Early-Fusion Foundation Models 893 Grad-CAM: Why did you say that? 894 ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for LanguageUnderstanding and Generation 895 Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection 896 U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation 897 Google COVID-19 Community Mobility Reports: Anonymization Process Description(version 1.1) 898 Interacting Quantum Observables: Categorical Algebra and Diagrammatics 899 Residual Gated Graph ConvNets 900 InterpretML: A Unified Framework for Machine Learning Interpretability 901 Lensless computational imaging through deep learning 902 Towards an Intelligent Edge: Wireless Communication Meets Machine Learning 903 TinyLlama: An Open-Source Small Language Model 904 Baseline Defenses for Adversarial Attacks Against Aligned Language Models 905 Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust DeepLearning 906 Bird Species Categorization Using Pose Normalized Deep Convolutional Nets 907 One-shot Learning with Memory-Augmented Neural Networks 908 TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems 909 Large Language Monkeys: Scaling Inference Compute with Repeated Sampling 910 A Simple Semi-Supervised Learning Framework for Object Detection 911 Behavior Trees in Robotics and AI: An Introduction 912 Twitter Sentiment Analysis: Lexicon Method, Machine Learning Method and TheirCombination 913 robosuite: A Modular Simulation Framework and Benchmark for Robot Learning 914 AlignedReID: Surpassing Human-Level Performance in Person Re-Identification 915 Learning to Generate Reviews and Discovering Sentiment 916 ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular PropertyPrediction 917 Massively Parallel Methods for Deep Reinforcement Learning 918 Domain Adaptation for Visual Applications: A Comprehensive Survey 919 INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTIONDataset in Interactive Driving Scenarios with Semantic 920 On the Min-cost Traveling Salesman Problem with Drone 921 EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models 922 Fractional Max-Pooling 923 LLM+P: Empowering Large Language Models with Optimal Planning Proficiency 924 Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models 925 Escaping the Big Data Paradigm with Compact Transformers 926 Scaling Laws for Autoregressive Generative Modeling 927 Super-Convergence: Very Fast Training of Neural Networks Using Large LearningRates 928 Optimization-Based Autonomous Racing of 1:43 Scale RC Cars 929 Ellipsis and Higher-Order Unification 930 AiiDA: Automated Interactive Infrastructure and Database for ComputationalScience 931 Sensing as a Service and Big Data 932 How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation 933 Text and Code Embeddings by Contrastive Pre-Training 934 Neural Operator: Learning Maps Between Function Spaces 935 YOLOv12: Attention-Centric Real-Time Object Detectors 936 LRS3-TED: a large-scale dataset for visual speech recognition 937 Fine-tune BERT for Extractive Summarization 938 The UEA multivariate time series classification archive, 2018 939 Deep Speaker: an End-to-End Neural Speaker Embedding System 940 Fake News Detection on Social Media using Geometric Deep Learning 941 Assessing BERT's Syntactic Abilities 942 Toy Models of Superposition 943 VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding inVideo-LLMs 944 RULER: What's the Real Context Size of Your Long-Context Language Models? 945 A Short Note on the Kinetics-700 Human Action Dataset 946 R2D2: Repeatable and Reliable Detector and Descriptor 947 MiniCPM: Unveiling the Potential of Small Language Models with Scalable TrainingStrategies 948 Understanding R1-Zero-Like Training: A Critical Perspective 949 Prompt Injection attack against LLM-integrated Applications 950 Scalable agent alignment via reward modeling: a research direction 951 TransferTransfo: A Transfer Learning Approach for Neural Network BasedConversational Agents 952 Solving math word problems with process- and outcome-based feedback 953 Multilingual Translation with Extensible Multilingual Pretraining and Finetuning 954 Towards a Definition of Disentangled Representations 955 Statistical guarantees for the EM algorithm: From population to sample-basedanalysis 956 The 2018 PIRM Challenge on Perceptual Image Super-resolution 957 Deep Transformer Models for Time Series Forecasting: The Influenza PrevalenceCase 958 Submanifold Sparse Convolutional Networks 959 Do Transformers Really Perform Bad for Graph Representation? 960 Sequential Matching Network: A New Architecture for Multi-turn ResponseSelection in Retrieval-based Chatbots 961 Basic Performance Measurements of the Intel Optane DC Persistent Memory Module 962 Three Factors Influencing Minima in SGD 963 Benchmarking Robustness in Object Detection: Autonomous Driving when Winter isComing 964 Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling 965 SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python 966 Threats to Federated Learning: A Survey 967 Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study 968 Zephyr: Direct Distillation of LM Alignment 969 StarCoder 2 and The Stack v2: The Next Generation 970 Stochastic Interpolants: A Unifying Framework for Flows and Diffusions 971 Massively Multitask Networks for Drug Discovery 972 COVID-ResNet: A Deep Learning Framework for Screening of COVID19 fromRadiographs 973 Wan: Open and Advanced Large-Scale Video Generative Models 974 Practical Black-Box Attacks against Machine Learning 975 Generalization in Deep Learning 976 High Quality Monocular Depth Estimation via Transfer Learning 977 MakeItTalk: Speaker-Aware Talking-Head Animation 978 Towards the Science of Security and Privacy in Machine Learning 979 Focal Self-attention for Local-Global Interactions in Vision Transformers 980 Revisiting Graph Neural Networks: All We Have is Low-Pass Filters 981 DenseBox: Unifying Landmark Localization with End to End Object Detection 982 Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences ofText-to-Image Synthesis 983 A micro Lie theory for state estimation in robotics 984 Client Selection in Federated Learning: Convergence Analysis and Power-of-ChoiceSelection Strategies 985 Hierarchical Multi-Scale Attention for Semantic Segmentation 986 End-to-end Continuous Speech Recognition using Attention-based Recurrent NN:First Results 987 Expanding the Reach of Federated Learning by Reducing Client ResourceRequirements 988 GPTs are GPTs: An Early Look at the Labor Market Impact Potential of LargeLanguage Models 989 Observation-based Cooperation Enforcement in Ad Hoc Networks 990 Hierarchical Deep Temporal Models for Group Activity Recognition 991 GANs Trained by a Two Time-Scale Update Rule Converge to a Local NashEquilibrium 992 Recent Advances in Autoencoder-Based Representation Learning 993 Cross-Age LFW: A Database for Studying Cross-Age Face Recognition inUnconstrained Environments 994 Video (language) modeling: a baseline for generative models of natural videos 995 Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-dataTasks 996 DeeperGCN: All You Need to Train Deeper GCNs 997 Fog Computing: Focusing on Mobile Users at the Edge 998 WebVision Database: Visual Learning and Understanding from Web Data 999 Deep Image Homography Estimation 1000 Places: An Image Database for Deep Scene Understanding 1001 Billion-scale semi-supervised learning for image classification 1002 CompressAI: a PyTorch library and evaluation platform for end-to-end compressionresearch 1003 Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model 1004 Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-BodyTeleoperation 1005 SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine 1006 Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation 1007 Concentrated Differential Privacy 1008 Local Rule-Based Explanations of Black Box Decision Systems 1009 Safe Exploration in Continuous Action Spaces 1010 Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers 1011 Document Expansion by Query Prediction 1012 Fog Computing: Principles, Architectures, and Applications 1013 A generic framework for privacy preserving deep learning 1014 Tensor Comprehensions: Framework-Agnostic High-Performance Machine LearningAbstractions 1015 SGDR: Stochastic Gradient Descent with Restarts 1016 Efficient Natural Language Response Suggestion for Smart Reply 1017 Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware AnomalyDetection 1018 Hello Edge: Keyword Spotting on Microcontrollers 1019 GPTFUZZER: Red Teaming Large Language Models with Auto-Generated JailbreakPrompts 1020 Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets 1021 Stochastic Adversarial Video Prediction 1022 Simple BERT Models for Relation Extraction and Semantic Role Labeling 1023 Deep Learning for Time-Series Analysis 1024 Data Decisions and Theoretical Implications when Adversarially Learning FairRepresentations 1025 Hyperparameter Search in Machine Learning 1026 Enigma: Decentralized Computation Platform with Guaranteed Privacy 1027 NoSQL Database: New Era of Databases for Big data Analytics - Classification,Characteristics and Comparison 1028 GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks 1029 Learn Convolutional Neural Network for Face Anti-Spoofing 1030 Data Augmentation by Pairing Samples for Images Classification 1031 Diffusion Adaptation over Networks 1032 Learning Models with Uniform Performance via Distributionally RobustOptimization 1033 Visual Semantic Role Labeling 1034 Contact Tracing Mobile Apps for COVID-19: Privacy Considerations and RelatedTrade-offs 1035 Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures 1036 SfM-Net: Learning of Structure and Motion from Video 1037 A Field Guide to Federated Optimization 1038 Towards Good Practices for Very Deep Two-Stream ConvNets 1039 Why do tree-based models still outperform deep learning on tabular data? 1040 Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks 1041 Masked Face Recognition Dataset and Application 1042 The Cosparse Analysis Model and Algorithms 1043 Fastfood: Approximate Kernel Expansions in Loglinear Time 1044 A Modern Introduction to Online Learning 1045 Incremental Gradient, Subgradient, and Proximal Methods for Convex Optimization:A Survey 1046 Convolutional Neural Networks using Logarithmic Data Representation 1047 Are we done with ImageNet? 1048 Secure Transmission with Multiple Antennas II: The MIMOME Wiretap Channel 1049 ActionCLIP: A New Paradigm for Video Action Recognition 1050 Analysis of Hashrate-Based Double Spending 1051 A Simple Method for Commonsense Reasoning 1052 A Categorical Archive of ChatGPT Failures 1053 A Normalized Gaussian Wasserstein Distance for Tiny Object Detection 1054 CNN-based Segmentation of Medical Imaging Data 1055 MagicVideo: Efficient Video Generation With Latent Diffusion Models 1056 Label-Consistent Backdoor Attacks 1057 Undefined By Data: A Survey of Big Data Definitions 1058 News Summarization and Evaluation in the Era of GPT-3 1059 The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CTSemantic Segmentations, and Surgical Outcomes 1060 Multi-Stage Document Ranking with BERT 1061 SQLNet: Generating Structured Queries From Natural Language WithoutReinforcement Learning 1062 Distilling Task-Specific Knowledge from BERT into Simple Neural Networks 1063 Thingi10K: A Dataset of 10,000 3D-Printing Models 1064 Massively Multilingual Neural Machine Translation in the Wild: Findings andChallenges 1065 A Fast Image Encryption Scheme based on Chaotic Standard Map 1066 Do CIFAR-10 Classifiers Generalize to CIFAR-10? 1067 Sharing is Caring: Efficient LM Post-Training with Collective RL ExperienceSharing 1068 The Dragon Hatchling: The Missing Link between the Transformer and Models of theBrain 1069 Less is More: Recursive Reasoning with Tiny Networks 1070 Vision Meets Drones: A Challenge 1071 Scalable Extraction of Training Data from (Production) Language Models 1072 Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? 1073 Spatial-Temporal Transformer Networks for Traffic Flow Forecasting 1074 DiffuserCam: Lensless Single-exposure 3D Imaging 1075 VIMA: General Robot Manipulation with Multimodal Prompts 1076 LSTM-based Deep Learning Models for Non-factoid Answer Selection 1077 Adversarial Perturbations Against Deep Neural Networks for MalwareClassification 1078 Breaking Monotony with Meaning: Motivation in Crowdsourcing Markets 1079 BAS: Beetle Antennae Search Algorithm for Optimization Problems 1080 Insecurity of Quantum Secure Computations 1081 Navigability of Complex Networks 1082 SIGN: Scalable Inception Graph Neural Networks 1083 A Survey of Structure from Motion 1084 Understanding Diffusion Models: A Unified Perspective 1085 Sora: A Review on Background, Technology, Limitations, and Opportunities ofLarge Vision Models 1086 A survey of dimensionality reduction techniques 1087 On Tiny Episodic Memories in Continual Learning 1088 Complexity Results and Practical Algorithms for Logics in KnowledgeRepresentation 1089 Boosting Trees for Anti-Spam Email Filtering 1090 Deep Reinforcement Learning from Self-Play in Imperfect-Information Games 1091 Opacus: User-Friendly Differential Privacy Library in PyTorch 1092 A2D2: Audi Autonomous Driving Dataset 1093 Pruning Convolutional Neural Networks for Resource Efficient Inference 1094 PyHST2: an hybrid distributed code for high speed tomographic reconstructionwith iterative reconstruction and a priori knowledge 1095 Towards 6G Networks: Use Cases and Technologies 1096 InternVideo: General Video Foundation Models via Generative and DiscriminativeLearning 1097 Introducing LETOR 4.0 Datasets 1098 Learning in Implicit Generative Models 1099 PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation 1100 A review of security attacks and Intrusion Detection Schemes in Wireless SensorNetworks 1101 One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI ExplainabilityTechniques 1102 Entity Embeddings of Categorical Variables 1103 Recommender Systems 1104 SpaceNet: A Remote Sensing Dataset and Challenge Series 1105 The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 1106 BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection 1107 Federated Learning of a Mixture of Global and Local Models 1108 Types of Cost in Inductive Concept Learning 1109 Multimodal datasets: misogyny, pornography, and malignant stereotypes 1110 Composable Effects for Flexible and Accelerated Probabilistic Programming inNumPyro 1111 UniVL: A Unified Video and Language Pre-Training Model for MultimodalUnderstanding and Generation 1112 A Survey on Neural Speech Synthesis 1113 Larger language models do in-context learning differently 1114 A geometric analysis of subspace clustering with outliers 1115 Isabelle: The Next 700 Theorem Provers 1116 A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models 1117 Image Restoration Using Convolutional Auto-encoders with Symmetric SkipConnections 1118 Top2Vec: Distributed Representations of Topics 1119 Deep Learning for Answer Sentence Selection 1120 Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-BasedRobotic Control 1121 FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces 1122 Learning Spatiotemporal Features with 3D Convolutional Networks 1123 An Efficient Graph Convolutional Network Technique for the Travelling SalesmanProblem 1124 Describe, Explain, Plan and Select: Interactive Planning with Large LanguageModels Enables Open-World Multi-Task Agents 1125 The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence 1126 A Novel Feature Extraction for Robust EMG Pattern Recognition 1127 SalGAN: Visual Saliency Prediction with Generative Adversarial Networks 1128 Gymnasium: A Standard Interface for Reinforcement Learning Environments 1129 Anomaly Detection using One-Class Neural Networks 1130 Explaining How a Deep Neural Network Trained with End-to-End Learning Steers aCar 1131 ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT 1132 Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Studyin Medicine 1133 Evaluation of Text Generation: A Survey 1134 CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs 1135 Algorithmic Fairness 1136 Hallucination is Inevitable: An Innate Limitation of Large Language Models 1137 Retrieval-Augmented Generation for AI-Generated Content: A Survey 1138 Some Like it Hoax: Automated Fake News Detection in Social Networks 1139 A Study on Overfitting in Deep Reinforcement Learning 1140 Good Friends, Bad News - Affect and Virality in Twitter 1141 Tensor Ring Decomposition 1142 Learning to Filter Spam E-Mail: A Comparison of a Naive Bayesian and aMemory-Based Approach 1143 ConvNet Architecture Search for Spatiotemporal Feature Learning 1144 Highly Scalable Deep Learning Training System with Mixed-Precision: TrainingImageNet in Four Minutes 1145 Forward-Mode Automatic Differentiation in Julia 1146 Time2Vec: Learning a Vector Representation of Time 1147 Integer Quantization for Deep Learning Inference: Principles and EmpiricalEvaluation 1148 Extended Object Tracking: Introduction, Overview and Applications 1149 Go-Explore: a New Approach for Hard-Exploration Problems 1150 Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims 1151 Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to StopWorrying and Love the Social and Behavioural Scienc 1152 Dynamic Spectrum Access: Signal Processing, Networking, and Regulatory Policy 1153 Speech Recognition by Machine, A Review 1154 A Gradient Descent Algorithm on the Grassman Manifold for Matrix Completion 1155 FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping 1156 DynGEM: Deep Embedding Method for Dynamic Graphs 1157 The Impact of AI on Developer Productivity: Evidence from GitHub Copilot 1158 A Study of BFLOAT16 for Deep Learning Training 1159 Explain Images with Multimodal Recurrent Neural Networks 1160 CryptoDL: Deep Neural Networks over Encrypted Data 1161 Open-Sora: Democratizing Efficient Video Production for All 1162 An Implementation of Intrusion Detection System Using Genetic Algorithm 1163 Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus(COVID-19) Detection 1164 A Survey on Large Language Models for Code Generation 1165 Blockchain in internet of things: Challenges and Solutions 1166 Shap-E: Generating Conditional 3D Implicit Functions 1167 From Classical to Quantum Shannon Theory 1168 Microsoft Malware Classification Challenge 1169 Emu3: Next-Token Prediction is All You Need 1170 Hierarchical Block Structures and High-resolution Model Selection in LargeNetworks 1171 Towards Understanding the Role of Over-Parametrization in Generalization ofNeural Networks 1172 Fast Patch-based Style Transfer of Arbitrary Style 1173 Rigid-Motion Scattering for Texture Classification 1174 Ranking spreaders by decomposing complex networks 1175 Shake-Shake regularization 1176 Data Mining: A prediction for performance improvement using classification 1177 A Review Paper: Noise Models in Digital Image Processing 1178 SAINT: Improved Neural Networks for Tabular Data via Row Attention andContrastive Pre-Training 1179 Improving Deep Learning using Generic Data Augmentation 1180 Slicing: A New Approach to Privacy Preserving Data Publishing 1181 DyNet: The Dynamic Neural Network Toolkit 1182 Deep Kalman Filters 1183 Protection Against Reconstruction and Its Applications in Private FederatedLearning 1184 Vertex-Frequency Analysis on Graphs 1185 A Deep Reinforcement Learning Framework for the Financial Portfolio ManagementProblem 1186 Robotic Tactile Perception of Object Properties: A Review 1187 On the Effects of Idiotypic Interactions for Recommendation Communities inArtificial Immune Systems 1188 NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles 1189 Understanding Adversarial Training: Increasing Local Stability of Neural Netsthrough Robust Optimization 1190 Machine Learning for Survival Analysis: A Survey 1191 Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyondthe Base Model? 1192 Light-Head R-CNN: In Defense of Two-Stage Object Detector 1193 FastFlow: Unsupervised Anomaly Detection and Localization via 2D NormalizingFlows 1194 Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison forDistorted Images 1195 Fully Convolutional Networks for Dense Semantic Labelling of High-ResolutionAerial Imagery 1196 Customized Segment Anything Model for Medical Image Segmentation 1197 Scalable, High-Quality Object Detection 1198 Analysis of Bitcoin Pooled Mining Reward Systems 1199 Benchmarking Model-Based Reinforcement Learning 1200 PaliGemma: A versatile 3B VLM for transfer 1201 SCAFFOLD: Stochastic Controlled Averaging for Federated Learning 1202 Document Embedding with Paragraph Vectors 1203 A General Optimization-based Framework for Global Pose Estimation with MultipleSensors 1204 LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large MultimodalModels 1205 On Neural Differential Equations 1206 Exploring the Landscape of Spatial Robustness 1207 BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers 1208 Equilibrated adaptive learning rates for non-convex optimization 1209 Cyber Security Awareness Campaigns: Why do they fail to change behaviour? 1210 Algorithms for multi-armed bandit problems 1211 False Information on Web and Social Media: A Survey 1212 Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and ModelPredictive Control 1213 SegDiff: Image Segmentation with Diffusion Probabilistic Models 1214 Re-evaluating Continual Learning Scenarios: A Categorization and Case for StrongBaselines 1215 The Why and How of Nonnegative Matrix Factorization 1216 Bots, #StrongerIn, and #Brexit: Computational Propaganda during the UK-EUReferendum 1217 Application of Deep Convolutional Neural Networks for Detecting Extreme Weatherin Climate Datasets 1218 Hands Deep in Deep Learning for Hand Pose Estimation 1219 Anti-Money Laundering in Bitcoin: Experimenting with Graph ConvolutionalNetworks for Financial Forensics 1220 Jailbreak and Guard Aligned Language Models with Only Few In-ContextDemonstrations 1221 Spectral Norm Regularization for Improving the Generalizability of Deep Learning 1222 Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca 1223 The latest gossip on BFT consensus 1224 Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System 1225 A Connection between Generative Adversarial Networks, Inverse ReinforcementLearning, and Energy-Based Models 1226 Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences 1227 Semantic Image Inpainting with Perceptual and Contextual Losses 1228 A General Optimization-based Framework for Local Odometry Estimation withMultiple Sensors 1229 Wide Activation for Efficient and Accurate Image Super-Resolution 1230 Equivalence Between Policy Gradients and Soft Q-Learning 1231 xView: Objects in Context in Overhead Imagery 1232 Aequitas: A Bias and Fairness Audit Toolkit 1233 SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning 1234 LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders 1235 A near-threshold RISC-V core with DSP extensions for scalable IoT EndpointDevices 1236 CERT: Contrastive Self-supervised Learning for Language Understanding 1237 Learning with a Strong Adversary 1238 The Cramer Distance as a Solution to Biased Wasserstein Gradients 1239 Image Segmentation by Using Threshold Techniques 1240 Robust subspace clustering 1241 FASTUS: A Cascaded Finite-State Transducer for Extracting Information fromNatural-Language Text 1242 Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferencesin Dialog 1243 A Benchmark Comparison of State-of-the-Practice Sentiment Analysis Methods 1244 GAIA-1: A Generative World Model for Autonomous Driving 1245 Fast and Uncertainty-Aware Directional Message Passing for Non-EquilibriumMolecules 1246 Fast YOLO: A Fast You Only Look Once System for Real-time Embedded ObjectDetection in Video 1247 Improving performance of CNN to predict likelihood of COVID-19 using chest X-rayimages with preprocessing algorithms 1248 Soft Actor-Critic for Discrete Action Settings 1249 Janus-Pro: Unified Multimodal Understanding and Generation with Data and ModelScaling 1250 Attention-based Graph Neural Network for Semi-supervised Learning 1251 Tulu 3: Pushing Frontiers in Open Language Model Post-Training 1252 Carbontracker: Tracking and Predicting the Carbon Footprint of Training DeepLearning Models 1253 Generative Language Modeling for Automated Theorem Proving 1254 Learning to Extract Keyphrases from Text 1255 A Practical Quantum Instruction Set Architecture 1256 1-Bit Matrix Completion 1257 PP-YOLOE: An evolved version of YOLO 1258 Regularization for Deep Learning: A Taxonomy 1259 Virtual KITTI 2 1260 Malicious URL Detection using Machine Learning: A Survey 1261 Evaluating Quality of Chatbots and Intelligent Conversational Agents 1262 Entropy-based Pruning of Backoff Language Models 1263 Face Expression Recognition and Analysis: The State of the Art 1264 CAM: Causal additive models, high-dimensional order search and penalizedregression 1265 PathVQA: 30000+ Questions for Medical Visual Question Answering 1266 Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs 1267 Learning to diagnose from scratch by exploiting dependencies among labels 1268 Aligning Text-to-Image Models using Human Feedback 1269 MCVD: Masked Conditional Video Diffusion for Prediction, Generation, andInterpolation 1270 Text-to-image Diffusion Models in Generative AI: A Survey 1271 Reinforced Self-Training (ReST) for Language Modeling 1272 Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes andFood Images 1273 InstantID: Zero-shot Identity-Preserving Generation in Seconds 1274 A Convex Framework for Fair Regression 1275 Cooperative SGD: A unified Framework for the Design and Analysis ofCommunication-Efficient SGD Algorithms 1276 Relation Classification via Recurrent Neural Network 1277 Uncovering the Limits of Adversarial Training against Norm-Bounded AdversarialExamples 1278 Machine learning \& artificial intelligence in the quantum domain 1279 Sparse Networks from Scratch: Faster Training without Losing Performance 1280 OpenAlex: A fully-open index of scholarly works, authors, venues, institutions,and concepts 1281 Attentive Pooling Networks 1282 Model-free control and intelligent PID controllers: towards a possibletrivialization of nonlinear control? 1283 Machine Learning-augmented Predictive Modeling of Turbulent Separated Flows overAirfoils 1284 Phi-4 Technical Report 1285 Automatic Liver and Tumor Segmentation of CT and MRI Volumes using CascadedFully Convolutional Neural Networks 1286 Simple Open-Vocabulary Object Detection with Vision Transformers 1287 GridMask Data Augmentation 1288 Inferring transportation modes from GPS trajectories using a convolutionalneural network 1289 MuRIL: Multilingual Representations for Indian Languages 1290 Topology Adaptive Graph Convolutional Networks 1291 A Cookbook of Self-Supervised Learning 1292 Self-critiquing models for assisting human evaluators 1293 Automatic summarising: factors and directions 1294 Deceiving Google's Perspective API Built for Detecting Toxic Comments 1295 One Model To Learn Them All 1296 Defensive Distillation is Not Robust to Adversarial Examples 1297 A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code 1298 Graph-Bert: Only Attention is Needed for Learning Graph Representations 1299 GSPBOX: A toolbox for signal processing on graphs 1300 The Forward-Forward Algorithm: Some Preliminary Investigations 1301 On the Definition of Cyber-Physical Resilience in Power Systems 1302 Visual Entailment: A Novel Task for Fine-Grained Image Understanding 1303 On the Properties of the Softmax Function with Application in Game Theory andReinforcement Learning 1304 Conditional Computation in Neural Networks for faster models 1305 Adversarial Attacks and Defences Competition 1306 NeMo: a toolkit for building AI applications using Neural Modules 1307 GraphCast: Learning skillful medium-range global weather forecasting 1308 Clingo = ASP + Control: Preliminary Report 1309 Multifaceted Feature Visualization: Uncovering the Different Types of FeaturesLearned By Each Neuron in Deep Neural Networks 1310 DHP Framework: Digital Health Passports Using Blockchain -- Use case oninternational tourism during the COVID-19 pandemic 1311 Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages 1312 Impact of Single Links in Competitive Percolation -- How complex networks growunder competition 1313 CLIP2Video: Mastering Video-Text Retrieval via Image CLIP 1314 BAGAN: Data Augmentation with Balancing GAN 1315 Large-scale Classification of Fine-Art Paintings: Learning The Right Metric onThe Right Feature 1316 ProcTHOR: Large-Scale Embodied AI Using Procedural Generation 1317 Towards Causal Representation Learning 1318 A Smart Home is No Castle: Privacy Vulnerabilities of Encrypted IoT Traffic 1319 Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents 1320 SFT Memorizes, RL Generalizes: A Comparative Study of Foundation ModelPost-training 1321 TensorFlow-Serving: Flexible, High-Performance ML Serving 1322 GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution 1323 Simple Baseline for Visual Question Answering 1324 The Spy in the Sandbox -- Practical Cache Attacks in Javascript 1325 Short Block-length Codes for Ultra-Reliable Low-Latency Communications 1326 Unsolved Problems in ML Safety 1327 Modeling and Propagating CNNs in a Tree Structure for Visual Tracking 1328 Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning 1329 Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking 1330 Structured sparsity through convex optimization 1331 CaloGAN: Simulating 3D High Energy Particle Showers in Multi-LayerElectromagnetic Calorimeters with Generative Adversarial Netwo 1332 Sentiment Analysis: Automatically Detecting Valence, Emotions, and OtherAffectual States from Text 1333 Pushing the limits of Full-duplex: Design and Real-time Implementation 1334 Recursively Summarizing Books with Human Feedback 1335 Is ChatGPT a Good Recommender? A Preliminary Study 1336 Sionna: An Open-Source Library for Next-Generation Physical Layer Research 1337 Classical simulation of noninteracting-fermion quantum circuits 1338 MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression 1339 DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced MultimodalUnderstanding 1340 A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI 1341 Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEGCompression 1342 Size reduction of complex networks preserving modularity 1343 Knowledge Distillation in Iterative Generative Models for Improved SamplingSpeed 1344 Simple random search provides a competitive approach to reinforcement learning 1345 BERT: A Review of Applications in Natural Language Processing and Understanding 1346 BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs 1347 Dpraodv: A Dyanamic Learning System Against Blackhole Attack in Aodv Based Manet 1348 Domain-Adversarial Neural Networks 1349 DenseNet: Implementing Efficient ConvNet Descriptor Pyramids 1350 The gem5 Simulator: Version 20.0+ 1351 Normalized Mutual Information to evaluate overlapping community findingalgorithms 1352 Fast low-rank estimation by projected gradient descent: General statistical andalgorithmic guarantees 1353 Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks 1354 Whitening Sentence Representations for Better Semantics and Faster Retrieval 1355 Detecting Language Model Attacks with Perplexity 1356 ReCoRD: Bridging the Gap between Human and Machine Commonsense ReadingComprehension 1357 Qwen2-Audio Technical Report 1358 An Overview of Deep Semi-Supervised Learning 1359 InternLM-XComposer2: Mastering Free-form Text-Image Composition andComprehension in Vision-Language Large Model 1360 Explainable AI for Trees: From Local Explanations to Global Understanding 1361 Demonstrate-Search-Predict: Composing retrieval and language models forknowledge-intensive NLP 1362 Traffic Light Control Using Deep Policy-Gradient and Value-Function BasedReinforcement Learning 1363 Uncertainty-Aware Reinforcement Learning for Collision Avoidance 1364 Not All Patches are What You Need: Expediting Vision Transformers via TokenReorganizations 1365 Beyond Skip Connections: Top-Down Modulation for Object Detection 1366 Federated Collaborative Filtering for Privacy-Preserving PersonalizedRecommendation System 1367 DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in CodeIntelligence 1368 Image compression and entanglement 1369 The Geometry of Truth: Emergent Linear Structure in Large Language ModelRepresentations of True/False Datasets 1370 AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale 1371 Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition 1372 High-Performance Neural Networks for Visual Object Classification 1373 Very Deep Convolutional Networks for Text Classification 1374 You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery 1375 L2 Regularization versus Batch and Weight Normalization 1376 Movie Gen: A Cast of Media Foundation Models 1377 An introduction to domain adaptation and transfer learning 1378 Dataset Distillation 1379 Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, MemoryEfficient, and Long Context Finetuning and Infer 1380 Federated Learning for Emoji Prediction in a Mobile Keyboard 1381 Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentationof Road Scenes 1382 Application of k Means Clustering algorithm for prediction of Students AcademicPerformance 1383 RewardBench: Evaluating Reward Models for Language Modeling 1384 Guided Image Generation with Conditional Invertible Neural Networks 1385 An exact mapping between the Variational Renormalization Group and Deep Learning 1386 Rényi Differential Privacy of the Sampled Gaussian Mechanism 1387 Seven Dimensions of Portability for Language Documentation and Description 1388 CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction 1389 Understanding and mitigating gradient pathologies in physics-informed neuralnetworks 1390 Hardware-oriented Approximation of Convolutional Neural Networks 1391 FastFCN: Rethinking Dilated Convolution in the Backbone for SemanticSegmentation 1392 Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes 1393 SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules 1394 Fully Connected Deep Structured Networks 1395 A Comprehensive Survey on Cross-modal Retrieval 1396 Deep Learning for Real-time Gravitational Wave Detection and ParameterEstimation: Results with Advanced LIGO Data 1397 WikiHow: A Large Scale Text Summarization Dataset 1398 PP-YOLO: An Effective and Efficient Implementation of Object Detector 1399 Anomaly Detection with Generative Adversarial Networks for Multivariate TimeSeries 1400 Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems 1401 ChatGPT is not all you need. A State of the Art Review of large Generative AImodels 1402 Design and analysis of experiments in networks: Reducing bias from interference 1403 Towards Robust Evaluations of Continual Learning 1404 Towards Measuring the Representation of Subjective Global Opinions in LanguageModels 1405 Moshi: a speech-text foundation model for real-time dialogue 1406 A Note on Over-Smoothing for Graph Neural Networks 1407 Privacy and Data Protection by Design - from policy to engineering 1408 GPT-Driver: Learning to Drive with GPT 1409 BERTje: A Dutch BERT Model 1410 Memory-based control with recurrent neural networks 1411 Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional NeuralNetworks 1412 MetNet: A Neural Weather Model for Precipitation Forecasting 1413 Vector Symbolic Architectures answer Jackendoff's challenges for cognitiveneuroscience 1414 Spatio-temporal video autoencoder with differentiable memory 1415 LIMO: Less is More for Reasoning 1416 Seq-NMS for Video Object Detection 1417 Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks 1418 DocBERT: BERT for Document Classification 1419 Deep learning to achieve clinically applicable segmentation of head and neckanatomy for radiotherapy 1420 Image Data Augmentation for Deep Learning: A Survey 1421 InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-viewLarge Reconstruction Models 1422 Grounded Language Learning in a Simulated 3D World 1423 Deep Learning Techniques for Music Generation -- A Survey 1424 Quantum Information Processing with Finite Resources -- Mathematical Foundations 1425 Group Sequence Policy Optimization 1426 Training-image based geostatistical inversion using a spatial generativeadversarial neural network 1427 Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models 1428 cleverhans v0.1: an adversarial machine learning library 1429 Glow: Graph Lowering Compiler Techniques for Neural Networks 1430 SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open BaseModels in the Wild 1431 High-order quantum algorithm for solving linear differential equations 1432 DeepSentiBank: Visual Sentiment Concept Classification with Deep ConvolutionalNeural Networks 1433 A first look at COVID-19 information and misinformation sharing on Twitter 1434 Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments,Analyses, and Improvement (v1.0) 1435 Pylearn2: a machine learning research library 1436 A Comprehensive Survey of Hallucination Mitigation Techniques in Large LanguageModels 1437 All-at-once Optimization for Coupled Matrix and Tensor Factorizations 1438 DFINITY Technology Overview Series, Consensus System 1439 Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12 1440 Understanding the planning of LLM agents: A survey 1441 AMMUS : A Survey of Transformer-based Pretrained Models in Natural LanguageProcessing 1442 Federated Evaluation of On-device Personalization 1443 Understanding the Capabilities, Limitations, and Societal Impact of LargeLanguage Models 1444 Jamba: A Hybrid Transformer-Mamba Language Model 1445 Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks 1446 Benchmarking in Manipulation Research: The YCB Object and Model Set andBenchmarking Protocols 1447 Using a Deep Reinforcement Learning Agent for Traffic Signal Control 1448 Doubly Robust Policy Evaluation and Optimization 1449 Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideasand Publications, and Bibliography for Explainab 1450 MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale 1451 Edward: A library for probabilistic modeling, inference, and criticism 1452 A comprehensive survey on point cloud registration 1453 MSR-net:Low-light Image Enhancement Using Deep Convolutional Network 1454 How (not) to Train your Generative Model: Scheduled Sampling, Likelihood,Adversary? 1455 Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks forEarly Rumor Detection 1456 CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research 1457 Adversarial Active Learning for Deep Networks: a Margin Based Approach 1458 MiniMax-01: Scaling Foundation Models with Lightning Attention 1459 Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language 1460 Projection onto the probability simplex: An efficient algorithm with a simpleproof, and an application 1461 A Simulation Model for the Waterfall Software Development Life Cycle 1462 A Primer on Cellular Network Analysis Using Stochastic Geometry 1463 Who's Harry Potter? Approximate Unlearning in LLMs 1464 DARTS+: Improved Differentiable Architecture Search with Early Stopping 1465 Benchmarking TPU, GPU, and CPU Platforms for Deep Learning 1466 Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 1467 The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits 1468 MultiModal-GPT: A Vision and Language Model for Dialogue with Humans 1469 YOLOv6 v3.0: A Full-Scale Reloading 1470 A Deeper Look at Experience Replay 1471 A Review of Safe Reinforcement Learning: Methods, Theory and Applications 1472 On the Convergence of Local Descent Methods in Federated Learning 1473 Explainable Artificial Intelligence: a Systematic Review 1474 The Power Grid Library for Benchmarking AC Optimal Power Flow Algorithms 1475 Music Source Separation in the Waveform Domain 1476 A New Local Adaptive Thresholding Technique in Binarization 1477 Loss Functions for Neural Networks for Image Processing 1478 Salvaging Federated Learning by Local Adaptation 1479 ABC-CNN: An Attention Based Convolutional Neural Network for Visual QuestionAnswering 1480 Adversarial Transformation Networks: Learning to Generate Adversarial Examples 1481 DINOv3 1482 From Code Foundation Models to Agents and Applications: A Comprehensive Surveyand Practical Guide to Code Intelligence 1483 DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome 1484 Analysis of Boolean Functions 1485 On Empirical Comparisons of Optimizers for Deep Learning 1486 Automated Dynamic Analysis of Ransomware: Benefits, Limitations and use forDetection 1487 PipeDream: Fast and Efficient Pipeline Parallel DNN Training 1488 Capsules for Object Segmentation 1489 MLIR: A Compiler Infrastructure for the End of Moore's Law 1490 ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks 1491 Dynamical Systems on Networks: A Tutorial 1492 Combinatorial Network Optimization with Unknown Variables: Multi-Armed Banditswith Linear Rewards 1493 Scaling Laws for Transfer 1494 Differential Privacy and Machine Learning: a Survey and Review 1495 $ N^4 $-Fields: Neural Network Nearest Neighbor Fields for Image Transforms 1496 Contextual Markov Decision Processes 1497 Understanding the Characteristics of Internet Short Video Sharing: YouTube as aCase Study 1498 DIODE: A Dense Indoor and Outdoor DEpth Dataset 1499 URLNet: Learning a URL Representation with Deep Learning for Malicious URLDetection 1500 Few-Shot Classification with Feature Map Reconstruction Networks 1501 Modeling the Multi-layer Nature of the European Air Transport Network:Resilience and Passengers Re-scheduling under random failu 1502 The jsonlite Package: A Practical and Consistent Mapping Between JSON Data and RObjects 1503 Fréchet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms 1504 Houdini: Fooling Deep Structured Prediction Models 1505 Smart Contract Templates: foundations, design landscape and research directions 1506 Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning 1507 Track Anything: Segment Anything Meets Videos 1508 Tight p-fusion frames 1509 Portuguese Named Entity Recognition using BERT-CRF 1510 State Evolution for General Approximate Message Passing Algorithms, withApplications to Spatial Coupling 1511 The Impact of Quantum Computing on Present Cryptography 1512 Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks,Baselines, and Building Blocks for Natural Language 1513 Comparing BERT against traditional machine learning text classification 1514 Data-efficient Deep Reinforcement Learning for Dexterous Manipulation 1515 Vision Transformer for Small-Size Datasets 1516 Flash Boys 2.0: Frontrunning, Transaction Reordering, and Consensus Instabilityin Decentralized Exchanges 1517 MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention 1518 Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for ContinuousControl 1519 The DeepFake Detection Challenge (DFDC) Dataset 1520 Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complexand Diverse Learning Environments and Their Solut 1521 BUT System Description to VoxCeleb Speaker Recognition Challenge 2019 1522 OTFS: A New Generation of Modulation Addressing the Challenges of 5G 1523 TrustLLM: Trustworthiness in Large Language Models 1524 Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learningon the Base Model 1525 Inpaint Anything: Segment Anything Meets Image Inpainting 1526 Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-boxInference Attacks against Centralized and Federated 1527 Multilingual E5 Text Embeddings: A Technical Report 1528 Haar Wavelet Based Approach for Image Compression and Quality Assessment ofCompressed Image 1529 Reinforcement and Imitation Learning via Interactive No-Regret Learning 1530 Lyapunov-based Safe Policy Optimization for Continuous Control 1531 Key Points Estimation and Point Instance Segmentation Approach for LaneDetection 1532 Inner-IoU: More Effective Intersection over Union Loss with Auxiliary BoundingBox 1533 CM-GANs: Cross-modal Generative Adversarial Networks for Common RepresentationLearning 1534 GEOM: Energy-annotated molecular conformations for property prediction andmolecular generation 1535 Transfusion: Predict the Next Token and Diffuse Images with One Multi-ModalModel 1536 Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild 1537 Benchmarking TinyML Systems: Challenges and Direction 1538 Polarized Self-Attention: Towards High-quality Pixel-wise Regression 1539 Survey of clustering algorithms for MANET 1540 RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose 1541 An Introduction to Collective Intelligence 1542 Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for DeepConvolutional Neural Network Models 1543 PCRNet: Point Cloud Registration Network using PointNet Encoding 1544 A Survey on Traffic Signal Control Methods 1545 ToolAlpaca: Generalized Tool Learning for Language Models with 3000 SimulatedCases 1546 Large Language Model Alignment: A Survey 1547 Generative Adversarial Imitation from Observation 1548 A simpler approach to obtaining an O(1/t) convergence rate for the projectedstochastic subgradient method 1549 Steganography An Art of Hiding Data 1550 BlenderBot 3: a deployed conversational agent that continually learns toresponsibly engage 1551 Efficient Exploration via State Marginal Matching 1552 Graph Neural Networks for Graphs with Heterophily: A Survey 1553 Short-term traffic flow forecasting with spatial-temporal correlation in ahybrid deep learning framework 1554 DeepInception: Hypnotize Large Language Model to Be Jailbreaker 1555 SIT: A Lightweight Encryption Algorithm for Secure Internet of Things 1556 The Principles of Deep Learning Theory 1557 Reinforcement Pre-Training 1558 Stacked What-Where Auto-encoders 1559 A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection 1560 Machine learning approach for text and document mining 1561 2017 Robotic Instrument Segmentation Challenge 1562 Did you hear that? Adversarial Examples Against Automatic Speech Recognition 1563 LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples 1564 Fixed-Form Variational Posterior Approximation through Stochastic LinearRegression 1565 Bridging the Gaps Between Residual Learning, Recurrent Neural Networks andVisual Cortex 1566 Auto-scaling Web Applications in Clouds: A Taxonomy and Survey 1567 PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human ActionUnderstanding 1568 Model-Free Episodic Control 1569 LLM in a flash: Efficient Large Language Model Inference with Limited Memory 1570 The Danger Theory and Its Application to Artificial Immune Systems 1571 VerilogEval: Evaluating Large Language Models for Verilog Code Generation 1572 Era of Big Data Processing: A New Approach via Tensor Networks and TensorDecompositions 1573 Facial Expression Recognition using Convolutional Neural Networks: State of theArt 1574 A Survey on 3D Gaussian Splatting 1575 Finding Covid-19 from Chest X-rays using Deep Learning on a Small Dataset 1576 Fractional Calculus In Image Processing: A Review 1577 FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 DaysLead 1578 Venture: a higher-order probabilistic programming platform with programmableinference 1579 Leveraging BERT for Extractive Text Summarization on Lectures 1580 Capabilities of Gemini Models in Medicine 1581 Data Mining: A Prediction for Performance Improvement of Engineering Studentsusing Classification 1582 End-to-end ASR: from Supervised to Semi-Supervised Learning with ModernArchitectures 1583 In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking 1584 Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training 1585 An Information Retrieval Approach to Short Text Conversation 1586 A Survey of Context Engineering for Large Language Models 1587 Nearest Neighbor Value Interpolation 1588 DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior 1589 Computing quantum discord is NP-complete 1590 Improving Efficient Neural Ranking Models with Cross-Architecture KnowledgeDistillation 1591 Learning to Detect Malicious Clients for Robust Federated Learning 1592 Interpretable & Explorable Approximations of Black Box Models 1593 Evaluating Large Language Models: A Comprehensive Survey 1594 Predicting the direction of stock market prices using random forest 1595 Large Language Model Guided Tree-of-Thought 1596 A continual learning survey: Defying forgetting in classification tasks 1597 Smart City Governance in Developing Countries: A Systematic Literature Review 1598 Transfer from Simulation to Real World through Learning Deep Inverse DynamicsModel 1599 Rethinking on Multi-Stage Networks for Human Pose Estimation 1600 The large learning rate phase of deep learning: the catapult mechanism 1601 CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained FaceDetection 1602 sktime: A Unified Interface for Machine Learning with Time Series 1603 Intern-S1: A Scientific Multimodal Foundation Model 1604 Training Large Language Models to Reason in a Continuous Latent Space 1605 DeepMind Lab 1606 THCHS-30 : A Free Chinese Speech Corpus 1607 Feature-Weighted Linear Stacking 1608 A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization 1609 Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning 1610 Overcoming Forgetting in Federated Learning on Non-IID Data 1611 Contrastive Training for Improved Out-of-Distribution Detection 1612 Multisided Fairness for Recommendation 1613 Improve Unsupervised Domain Adaptation with Mixup Training 1614 Ground-state energy estimation of the water molecule on a trapped ion quantumcomputer 1615 Automatically Correcting Large Language Models: Surveying the landscape ofdiverse self-correction strategies 1616 HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge 1617 Unlocking High-Accuracy Differentially Private Image Classification throughScale 1618 FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework forMulti-Task and Multi-Domain Scenarios 1619 Low-Resource Languages Jailbreak GPT-4 1620 A Performance Comparison of CUDA and OpenCL 1621 Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits ofHighly Effective STaRs 1622 MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust toAdversarial Examples 1623 Ablation Studies in Artificial Neural Networks 1624 Massive MIMO with 1-bit ADC 1625 Forecasting Economics and Financial Time Series: ARIMA vs. LSTM 1626 Neural Reflectance Fields for Appearance Acquisition 1627 Temporal 3D ConvNets: New Architecture and Transfer Learning for VideoClassification 1628 How do Humans Understand Explanations from Machine Learning Systems? AnEvaluation of the Human-Interpretability of Explanation 1629 LadderNet: Multi-path networks based on U-Net for medical image segmentation 1630 A Survey on Retrieval-Augmented Text Generation 1631 UAV Networks Surveillance Implementing an Effective Load-Aware Multipath RoutingProtocol (ELAMRP) 1632 Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds 1633 MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments 1634 Probabilistic two-stage detection 1635 A Deterministic Approach to Wireless Relay Networks 1636 MoE-LLaVA: Mixture of Experts for Large Vision-Language Models 1637 SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model 1638 Binary Patterns Encoded Convolutional Neural Networks for Texture Recognitionand Remote Sensing Scene Classification 1639 NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (UpdatedPost-Gaussian Splatting) 1640 On weight initialization in deep neural networks 1641 Application of Quantum Annealing to Training of Deep Neural Networks 1642 An Open Source AutoML Benchmark 1643 Gotta Go Fast When Generating Data with Score-Based Models 1644 MemGPT: Towards LLMs as Operating Systems 1645 Llama 2: Open Foundation and Fine-Tuned Chat Models 1646 Survey on Factuality in Large Language Models: Knowledge, Retrieval andDomain-Specificity 1647 Physics-Informed Neural Network for Modelling the Thermochemical Curing Processof Composite-Tool Systems During Manufacture 1648 PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering 1649 Structured Sparse Method for Hyperspectral Unmixing 1650 A Review Paper on Oculus Rift-A Virtual Reality Headset 1651 All You Need is "Love": Evading Hate-speech Detection 1652 Fast global convergence of gradient methods for high-dimensional statisticalrecovery 1653 Spying on the Smart Home: Privacy Attacks and Defenses on Encrypted IoT Traffic 1654 A Simple, Fast Diverse Decoding Algorithm for Neural Generation 1655 "I think this is the most disruptive technology": Exploring Sentiments ofChatGPT Early Adopters using Twitter Data 1656 Speech Recognition by Composition of Weighted Finite Automata 1657 Personal LLM Agents: Insights and Survey about the Capability, Efficiency andSecurity 1658 Fast Computation of Moore-Penrose Inverse Matrices 1659 A Survey of Reinforcement Learning from Human Feedback 1660 A simple but tough-to-beat baseline for the Fake News Challenge stance detectiontask 1661 VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model 1662 A Field Guide to Forward-Backward Splitting with a FASTA Implementation 1663 Exploring the Mobility of Mobile Phone Users 1664 Research Challenges for Enterprise Cloud Computing 1665 CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims 1666 M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems 1667 Numerical Weather Prediction (NWP) and hybrid ARMA/ANN model to predict globalradiation 1668 DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models 1669 NEOS Server 4.0 Administrative Guide 1670 Scaling Synthetic Data Creation with 1,000,000,000 Personas 1671 Large Language Diffusion Models 1672 ModelChain: Decentralized Privacy-Preserving Healthcare Predictive ModelingFramework on Private Blockchain Networks 1673 Learning a Text-Video Embedding from Incomplete and Heterogeneous Data 1674 Active sequential hypothesis testing 1675 Targeting Ultimate Accuracy: Face Recognition via Deep Embedding 1676 Learning Likelihoods with Conditional Normalizing Flows 1677 A Deep Reinforcement Learning Chatbot 1678 CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models 1679 Torchattacks: A PyTorch Repository for Adversarial Attacks 1680 New Comparative Study Between DES, 3DES and AES within Nine Factors 1681 A Primer on the Signature Method in Machine Learning 1682 MISSFormer: An Effective Medical Image Segmentation Transformer 1683 Optimal Rates of Convergence for Noisy Sparse Phase Retrieval via ThresholdedWirtinger Flow 1684 AutoAssign: Differentiable Label Assignment for Dense Object Detection 1685 Maximum-Likelihood Augmented Discrete Generative Adversarial Networks 1686 GAIA: a benchmark for General AI Assistants 1687 Red-Teaming the Stable Diffusion Safety Filter 1688 VANET Routing Protocols: Pros and Cons 1689 Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLPResearchers 1690 Generative replay with feedback connections as a general strategy for continuallearning 1691 Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong 1692 Unmasking DeepFakes with simple Features 1693 Survey on Feature Selection 1694 Variations of the Similarity Function of TextRank for Automated Summarization 1695 Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: ACritical Review and Assessment 1696 Constructions from Dots and Lines 1697 Data for Development: the D4D Challenge on Mobile Phone Data 1698 Robust Federated Learning in a Heterogeneous Environment 1699 Machine Learning for Precipitation Nowcasting from Radar Images 1700 Learning to Optimize Join Queries With Deep Reinforcement Learning 1701 Turning Internet of Things(IoT) into Internet of Vulnerabilities (IoV) : IoTBotnets 1702 Deep Learning with Domain Adaptation for Accelerated Projection-ReconstructionMR 1703 Recipes for Safety in Open-domain Chatbots 1704 Quantifying synergistic mutual information 1705 Trends in crypto-currencies and blockchain technologies: A monetary theory andregulation perspective 1706 Valley: Video Assistant with Large Language model Enhanced abilitY 1707 Identifying Influential Spreaders by Weighted LeaderRank 1708 Spatial Group-wise Enhance: Improving Semantic Feature Learning in ConvolutionalNetworks 1709 No bad local minima: Data independent training error guarantees for multilayerneural networks 1710 $π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization 1711 MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training 1712 Spatially-sparse convolutional neural networks 1713 Segment and Track Anything 1714 GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning withScalable Reinforcement Learning 1715 The scaling of human mobility by taxis is exponential 1716 Toward Transformer-Based Object Detection 1717 Demystifying Long Chain-of-Thought Reasoning in LLMs 1718 RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation 1719 A Large Dataset of Object Scans 1720 BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19patients 1721 Real-world Noisy Image Denoising: A New Benchmark 1722 Sharp thresholds for high-dimensional and noisy recovery of sparsity 1723 Qwen3 Embedding: Advancing Text Embedding and Reranking Through FoundationModels 1724 SegGPT: Segmenting Everything In Context 1725 Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions 1726 High-Resolution Breast Cancer Screening with Multi-View Deep ConvolutionalNeural Networks 1727 ECG arrhythmia classification using a 2-D convolutional neural network 1728 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model 1729 Provable approximation properties for deep neural networks 1730 k-core decomposition: a tool for the visualization of large scale networks 1731 TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoorsin AI Systems 1732 Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models 1733 Graph-Cover Decoding and Finite-Length Analysis of Message-Passing IterativeDecoding of LDPC Codes 1734 Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens 1735 Less-forgetting Learning in Deep Neural Networks 1736 Understanding Membership Inferences on Well-Generalized Learning Models 1737 A survey on algorithmic aspects of modular decomposition 1738 VIOLET : End-to-End Video-Language Transformers with Masked Visual-tokenModeling 1739 Noise2Music: Text-conditioned Music Generation with Diffusion Models 1740 Efficient Few-Shot Learning Without Prompts 1741 Motivating the Rules of the Game for Adversarial Example Research 1742 Model-assisted cohort selection with bias analysis for generating large-scalecohorts from the EHR for oncology research 1743 Modifying Memories in Transformer Models 1744 HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network thatAchieves over 0.9 Mean Dice and 86 FPS 1745 One-Shot Federated Learning 1746 Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges 1747 Application of Convolutional Neural Network to Predict Airfoil Lift Coefficient 1748 Neural Stochastic Differential Equations: Deep Latent Gaussian Models in theDiffusion Limit 1749 A Description Logic Primer 1750 Acme: A Research Framework for Distributed Reinforcement Learning 1751 Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and aUnified Framework 1752 Well-Read Students Learn Better: On the Importance of Pre-training CompactModels 1753 PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models withAuto-parallel Computation 1754 BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-CentricAutonomous Driving 1755 Real-time optimal control via Deep Neural Networks: study on landing problems 1756 P+: Extended Textual Conditioning in Text-to-Image Generation 1757 TorchMD-NET: Equivariant Transformers for Neural Network based MolecularPotentials 1758 CycleGAN, a Master of Steganography 1759 On the Origin of Deep Learning 1760 Mahotas: Open source software for scriptable computer vision 1761 Relational Deep Reinforcement Learning 1762 Process Mining for Python (PM4Py): Bridging the Gap Between Process- and DataScience 1763 Asymptotic normality of maximum likelihood and its variational approximation forstochastic blockmodels 1764 Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders 1765 Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning 1766 Collaborative Representation based Classification for Face Recognition 1767 Predictive Inequity in Object Detection 1768 Odeint - Solving ordinary differential equations in C++ 1769 Small world yields the most effective information spreading 1770 Face Behavior a la carte: Expressions, Affect and Action Units in a SingleNetwork 1771 Depth Pro: Sharp Monocular Metric Depth in Less Than a Second 1772 Towards Deep Symbolic Reinforcement Learning 1773 An Empirical Study of Real-World SPARQL Queries 1774 Classification of Alzheimer's Disease using fMRI Data and Deep LearningConvolutional Neural Networks 1775 PersonNet: Person Re-identification with Deep Convolutional Neural Networks 1776 Testing Deep Neural Networks 1777 Learning a Driving Simulator 1778 Spatio-Temporal Analysis of Epidemic Phenomena Using the R Package surveillance 1779 e3nn: Euclidean Neural Networks 1780 Enhanced discrete particle swarm optimization path planning for UAV vision-basedsurface inspection 1781 Capsule Network Performance on Complex Data 1782 MNIST-C: A Robustness Benchmark for Computer Vision 1783 $τ$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains 1784 Chip Placement with Deep Reinforcement Learning 1785 Personalized Recommendation via Integrated Diffusion on User-Item-Tag TripartiteGraphs 1786 Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec LanguageModeling 1787 Rearrangement: A Challenge for Embodied AI 1788 Unit Test Case Generation with Transformers and Focal Context 1789 Conditional Image Generation with Score-Based Diffusion Models 1790 On 'A Kalman Filter-Based Algorithm for IMU-Camera Calibration: ObservabilityAnalysis and Performance Evaluation' 1791 An Overview of Catastrophic AI Risks 1792 Less Is More: Fast Multivariate Time Series Forecasting with LightSampling-oriented MLP Structures 1793 Query2Label: A Simple Transformer Way to Multi-Label Classification 1794 An Improved k-Nearest Neighbor Algorithm for Text Categorization 1795 Audiovisual SlowFast Networks for Video Recognition 1796 SGPT: GPT Sentence Embeddings for Semantic Search 1797 CDN: Content Distribution Network 1798 Pretrained Transformers as Universal Computation Engines 1799 Tree-Structured Parzen Estimator: Understanding Its Algorithm Components andTheir Roles for Better Empirical Performance 1800 A Review of Control Algorithms for Autonomous Quadrotors 1801 Learning from Few Examples: A Summary of Approaches to Few-Shot Learning 1802 Respecting causality is all you need for training physics-informed neuralnetworks 1803 ETSformer: Exponential Smoothing Transformers for Time-series Forecasting 1804 A Survey of Millimeter Wave (mmWave) Communications for 5G: Opportunities andChallenges 1805 Generating images with recurrent adversarial networks 1806 Understanding the Behaviors of BERT in Ranking 1807 Relevance of Unsupervised Metrics in Task-Oriented Dialogue for EvaluatingNatural Language Generation 1808 End-to-End Deep Learning for Person Search 1809 Dissociating language and thought in large language models 1810 The Degrees of Freedom Regions of MIMO Broadcast, Interference, and CognitiveRadio Channels with No CSIT 1811 Multi-Task Cross-Lingual Sequence Tagging from Scratch 1812 Is ChatGPT the Ultimate Programming Assistant -- How far is it? 1813 Generative Poisoning Attack Method Against Neural Networks 1814 Towards Understanding Generalization of Deep Learning: Perspective of LossLandscapes 1815 A scalable verification solution for blockchains 1816 Detecting tiny objects in aerial images: A normalized Wasserstein distance and anew benchmark 1817 Fast Hands-free Writing by Gaze Direction 1818 The Cost of Training NLP Models: A Concise Overview 1819 Stop Explaining Black Box Machine Learning Models for High Stakes Decisions andUse Interpretable Models Instead 1820 Continuous Variable Quantum Cryptography using Two-Way Quantum Communication 1821 Deep Learning Based MIMO Communications 1822 Emergent Multi-Agent Communication in the Deep Learning Era 1823 The Landscape of Agentic Reinforcement Learning for LLMs: A Survey 1824 Delta Tuning: A Comprehensive Study of Parameter Efficient Methods forPre-trained Language Models 1825 Ranking the spreading influence in complex networks 1826 ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning 1827 Towards Crafting Text Adversarial Samples 1828 VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and VideoUnderstanding 1829 A Modern Primer on Processing in Memory 1830 Word Embeddings: A Survey 1831 Bitcoin Transaction Graph Analysis 1832 Deepfake Video Detection Using Convolutional Vision Transformer 1833 SigNet: Convolutional Siamese Network for Writer Independent Offline SignatureVerification 1834 SemDeDup: Data-efficient learning at web-scale through semantic deduplication 1835 Using data mining techniques for diagnosis and prognosis of cancer disease 1836 rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking 1837 Real-time object detection method based on improved YOLOv4-tiny 1838 Adaptive Affinity Propagation Clustering 1839 CameraCtrl: Enabling Camera Control for Text-to-Video Generation 1840 DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker 1841 Efficient Character-level Document Classification by Combining Convolution andRecurrent Layers 1842 Bitwise Neural Networks 1843 Numerical Coordinate Regression with Convolutional Neural Networks 1844 Multi-class Generative Adversarial Networks with the L2 Loss Function 1845 Universality in polytope phase transitions and message passing algorithms 1846 Hierarchical Clustering Using Mutual Information 1847 Ranking in evolving complex networks 1848 Z-Image: An Efficient Image Generation Foundation Model with Single-StreamDiffusion Transformer 1849 Semantic Specialisation of Distributional Word Vector Spaces using Monolingualand Cross-Lingual Constraints 1850 A Survey on Hallucination in Large Vision-Language Models 1851 Texture Synthesis with Spatial Generative Adversarial Networks 1852 Learning to Protect Communications with Adversarial Neural Cryptography 1853 Detection of Unauthorized IoT Devices Using Machine Learning Techniques 1854 Scene Text Detection via Holistic, Multi-Channel Prediction 1855 Seed-TTS: A Family of High-Quality Versatile Speech Generation Models 1856 The role of centrality for the identification of influential spreaders incomplex networks 1857 Faster gaze prediction with dense networks and Fisher pruning 1858 Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models viaMixture-of-LoRAs 1859 Mutarjim: Advancing Bidirectional Arabic-English Translation with a SmallLanguage Model 1860 Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global WeatherForecast 1861 SantaCoder: don't reach for the stars! 1862 Personalized Search 1863 Generalization and Regularization in DQN 1864 Query-Efficient Imitation Learning for End-to-End Autonomous Driving 1865 Preserving Causal Constraints in Counterfactual Explanations for MachineLearning Classifiers 1866 Background Suppression Network for Weakly-supervised Temporal ActionLocalization 1867 A Convolutional Neural Network Neutrino Event Classifier 1868 M$^2$BEV: Multi-Camera Joint 3D Detection and Segmentation with UnifiedBirds-Eye View Representation 1869 Open Problems in Cooperative AI 1870 Forecasting Global Weather with Graph Neural Networks 1871 LSB: A Lightweight Scalable BlockChain for IoT Security and Privacy 1872 Mobile Device Identification via Sensor Fingerprinting 1873 Introduction to Tensor Decompositions and their Applications in Machine Learning 1874 Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning 1875 LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods 1876 Texture image analysis and texture classification methods - A review 1877 Ubiquitous Smart Home System Using Android Application 1878 eXpose: A Character-Level Convolutional Neural Network with Embeddings ForDetecting Malicious URLs, File Paths and Registry Keys 1879 A Survey of Deep Reinforcement Learning in Video Games 1880 FoveaBox: Beyond Anchor-based Object Detector 1881 Real-time Distracted Driver Posture Classification 1882 On Subversive Miner Strategies and Block Withholding Attack in Bitcoin DigitalCurrency 1883 PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark forFinance 1884 Learning to learn with quantum neural networks via classical neural networks 1885 Pyramidal Convolution: Rethinking Convolutional Neural Networks for VisualRecognition 1886 Self-concordant analysis for logistic regression 1887 Efficient Optimal Algorithm of Task Scheduling in Cloud Computing Environment 1888 Exploiting problem structure in a genetic algorithm approach to a nurserostering problem 1889 How to Simulate Billiards and Similar Systems 1890 Full-Duplex Mobile Device - Pushing the Limits 1891 Deep Successor Reinforcement Learning 1892 Occupancy Grids: A Stochastic Spatial Representation for Active Robot Perception 1893 LIQUi|>: A Software Design Architecture and Domain-Specific Language for QuantumComputing 1894 CMA-ES for Hyperparameter Optimization of Deep Neural Networks 1895 Improving Robustness Without Sacrificing Accuracy with Patch GaussianAugmentation 1896 Combinatorial Optimization by Graph Pointer Networks and HierarchicalReinforcement Learning 1897 ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical ImageRegistration 1898 PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection 1899 DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving 1900 Improving Language Model Negotiation with Self-Play and In-Context Learning fromAI Feedback 1901 Breast Mass Classification from Mammograms using Deep Convolutional NeuralNetworks 1902 Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art 1903 Learning and Evaluating General Linguistic Intelligence 1904 Learning to Evade Static PE Machine Learning Malware Models via ReinforcementLearning 1905 Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs 1906 UI-TARS: Pioneering Automated GUI Interaction with Native Agents 1907 Contextual LSTM (CLSTM) models for Large scale NLP tasks 1908 FusionNet: 3D Object Classification Using Multiple Data Representations 1909 On Fast Sampling of Diffusion Probabilistic Models 1910 Data Augmentation Using GANs 1911 Limitations of Agile Software Processes 1912 ChipNeMo: Domain-Adapted LLMs for Chip Design 1913 Open-Ended Learning Leads to Generally Capable Agents 1914 A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs byValidating Low-Confidence Generation 1915 ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, RequirementsElicitation, and Software Design 1916 Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks 1917 Explore Spatiotemporal and Demographic Characteristics of Human Mobility viaTwitter: A Case Study of Chicago 1918 An Explainable Artificial Intelligence Approach for Unsupervised Fault Detectionand Diagnosis in Rotating Machinery 1919 Artificial Neural Networks-Based Machine Learning for Wireless Networks: ATutorial 1920 Sockeye: A Toolkit for Neural Machine Translation 1921 Seamless: Multilingual Expressive and Streaming Speech Translation 1922 Beyond citations: Scholars' visibility on the social Web 1923 Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR SemanticSegmentation 1924 Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling 1925 Does Synthetic Data Generation of LLMs Help Clinical Text Mining? 1926 CodeGen2: Lessons for Training LLMs on Programming and Natural Languages 1927 Fast Guided Filter 1928 Segmentation and Classification of Skin Lesions for Disease Diagnosis 1929 SMARTS: Scalable Multi-Agent Reinforcement Learning Training School forAutonomous Driving 1930 The Devil is in the Tails: Fine-grained Classification in the Wild 1931 Tower: An Open Multilingual Large Language Model for Translation-Related Tasks 1932 A General Algorithm for Deciding Transportability of Experimental Results 1933 A Survey of Predictive Modelling under Imbalanced Distributions 1934 A Comparative Study of Load Balancing Algorithms in Cloud Computing Environment 1935 LaneNet: Real-Time Lane Detection Networks for Autonomous Driving 1936 Deep Learning Approximation for Stochastic Control Problems 1937 A Note on the PAC Bayesian Theorem 1938 Low-resource Languages: A Review of Past Work and Future Challenges 1939 Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing 1940 SEED-X: Multimodal Models with Unified Multi-granularity Comprehension andGeneration 1941 SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval 1942 Generative Agent Simulations of 1,000 People 1943 Complexity and Philosophy 1944 SVD Based Image Processing Applications: State of The Art, Contributions andResearch Challenges 1945 Machine Learning for Synthetic Data Generation: A Review 1946 Variance Reduction in SGD by Distributed Importance Sampling 1947 Forecasting day-ahead electricity prices in Europe: the importance ofconsidering market integration 1948 A Photometrically Calibrated Benchmark For Monocular Visual Odometry 1949 Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraftCombat Games 1950 A Survey on Knowledge Distillation of Large Language Models 1951 Learning human behaviors from motion capture by adversarial imitation 1952 Recurrent Neural Networks (RNNs): A gentle Introduction and Overview 1953 Combining Naive Bayes and Decision Tree for Adaptive Intrusion Detection 1954 RFAConv: Innovating Spatial Attention and Standard Convolutional Operation 1955 LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving 1956 Robust network community detection using balanced propagation 1957 DDD17: End-To-End DAVIS Driving Dataset 1958 An Introduction to Probabilistic Programming 1959 Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference 1960 Strong Secrecy from Channel Resolvability 1961 Relational Graph Attention Networks 1962 Solving the Problem of the K Parameter in the KNN Classifier Using an EnsembleLearning Approach 1963 Exploring and Evaluating Hallucinations in LLM-Powered Code Generation 1964 Selective review of offline change point detection methods 1965 Deep Residual Learning for Compressed Sensing CT Reconstruction via PersistentHomology Analysis 1966 Dreamix: Video Diffusion Models are General Video Editors 1967 Hypothesis Testing for Automated Community Detection in Networks 1968 CLEAR: Character Unlearning in Textual and Visual Modalities 1969 Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks 1970 Survey of Vulnerabilities in Large Language Models Revealed by AdversarialAttacks 1971 Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth 1972 The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions 1973 Exact and Stable Recovery of Rotations for Robust Synchronization 1974 Chiron: Privacy-preserving Machine Learning as a Service 1975 Language models show human-like content effects on reasoning tasks 1976 MedDialog: Two Large-scale Medical Dialogue Datasets 1977 WT5?! Training Text-to-Text Models to Explain their Predictions 1978 Federated Learning for Internet of Things: Applications, Challenges, andOpportunities 1979 GPT4Graph: Can Large Language Models Understand Graph Structured Data ? AnEmpirical Evaluation and Benchmarking 1980 DoWhy: An End-to-End Library for Causal Inference 1981 IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies 1982 Parsimonious shooting heuristic for trajectory control of connected automatedtraffic part I: Theoretical analysis with generaliz 1983 Spreading dynamics in complex networks 1984 Training Deeper Convolutional Networks with Deep Supervision 1985 GraphNVP: An Invertible Flow Model for Generating Molecular Graphs 1986 Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning 1987 Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensionalPartial Differential Equations 1988 A survey of robot learning from demonstrations for Human-Robot Collaboration 1989 The BOSARIS Toolkit: Theory, Algorithms and Code for Surviving the New DCF 1990 Detailed comparison of communication efficiency of split learning and federatedlearning 1991 MonALISA : A Distributed Monitoring Service Architecture 1992 DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4 1993 Neural Networks in Mobile Robot Motion 1994 InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning,and Efficiency 1995 Assessing requirements to scale to practical quantum advantage 1996 Quantum circuits of T-depth one 1997 Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning 1998 Introduction to the Bag of Features Paradigm for Image Classification andRetrieval 1999 Generative and Discriminative Text Classification with Recurrent Neural Networks 2000 Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19Chest CT Images 2001 Semantically Self-Aligned Network for Text-to-Image Part-aware PersonRe-identification 2002 Mask2Former for Video Instance Segmentation 2003 A Living Review of Machine Learning for Particle Physics 2004 PanNuke Dataset Extension, Insights and Baselines 2005 A Survey of Downlink Non-orthogonal Multiple Access for 5G WirelessCommunication Networks 2006 Agentless: Demystifying LLM-based Software Engineering Agents 2007 Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies 2008 Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3DMedical Data 2009 Human-Data Interaction: The Human Face of the Data-Driven Society 2010 Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View 2011 InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction 2012 Deep Neural Networks to Enable Real-time Multimessenger Astrophysics 2013 The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, andBoosting: Tutorial 2014 A General Approach to Adding Differential Privacy to Iterative TrainingProcedures 2015 EU regulations on algorithmic decision-making and a "right to explanation" 2016 Convergence Rate of Frank-Wolfe for Non-Convex Objectives 2017 A Berkeley View of Systems Challenges for AI 2018 R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-ModalFormalization 2019 SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data DrugDiscovery 2020 Congestion Avoidance in Computer Networks with a Connectionless Network Layer 2021 Tensor Programs V: Tuning Large Neural Networks via Zero-Shot HyperparameterTransfer 2022 Link prediction in complex networks: a local na\"ıve Bayes model 2023 A Review of Software Quality Models for the Evaluation of Software Products 2024 Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation 2025 Scheduling for Cellular Federated Edge Learning with Importance and ChannelAwareness 2026 A CHAID Based Performance Prediction Model in Educational Data Mining 2027 Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer 2028 Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and DeepResidual Networks 2029 Pythia v0.1: the Winning Entry to the VQA Challenge 2018 2030 A Review on Language Models as Knowledge Bases 2031 DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task 2032 ChemBERTa-2: Towards Chemical Foundation Models 2033 Collecting and Analyzing Data from Smart Device Users with Local DifferentialPrivacy 2034 Pretrained Language Models for Text Generation: A Survey 2035 Speculative Buffer Overflows: Attacks and Defenses 2036 Don't Make Your LLM an Evaluation Benchmark Cheater 2037 Supervised Classification Performance of Multispectral Images 2038 A Comparative Study of Polar Code Constructions for the AWGN Channel 2039 Use of a Capsule Network to Detect Fake Images and Videos 2040 Adversarial Unlearning of Backdoors via Implicit Hypergradient 2041 Fast Domain Adaptation for Neural Machine Translation 2042 A Comprehensive Study of Deep Video Action Recognition 2043 Botnet-based Distributed Denial of Service (DDoS) Attacks on Web Servers:Classification and Art 2044 Towards Verified Artificial Intelligence 2045 Adversarial Training for Large Neural Language Models 2046 RECOMP: Improving Retrieval-Augmented LMs with Compression and SelectiveAugmentation 2047 Semantic Instance Segmentation via Deep Metric Learning 2048 Building a Conversational Agent Overnight with Dialogue Self-Play 2049 Debugging Backwards in Time 2050 Automated identification and characterization of parcels (AICP) withOpenStreetMap and Points of Interest 2051 Direct Language Model Alignment from Online AI Feedback 2052 Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation 2053 Towards Realistic Individual Recourse and Actionable Explanations in Black-BoxDecision Making Systems 2054 Learning Thermodynamics with Boltzmann Machines 2055 Self-Supervised Learning with Swin Transformers 2056 Decentralized Federated Learning: A Segmented Gossip Approach 2057 Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec 2058 Macro F1 and Macro F1 2059 Process Reinforcement through Implicit Rewards 2060 Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity 2061 Context-Aware Sentence/Passage Term Importance Estimation For First StageRetrieval 2062 A Simple Neural Attentive Meta-Learner 2063 Large-Scale Screening of COVID-19 from Community Acquired Pneumonia usingInfection Size-Aware Classification 2064 From sequential decoding to channel polarization and back again 2065 The role of twitter in the life cycle of a scientific publication 2066 Postprocessing for quantum random number generators: entropy evaluation andrandomness extraction 2067 Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment 2068 Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive 2069 Linear and Order Statistics Combiners for Pattern Classification 2070 Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging 2071 A Comprehensive guide to Bayesian Convolutional Neural Network with VariationalInference 2072 Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization 2073 A Review of Financial Accounting Fraud Detection based on Data Mining Techniques 2074 Foundation Models for Decision Making: Problems, Methods, and Opportunities 2075 DataFlow: An LLM-Driven Framework for Unified Data Preparation and WorkflowAutomation in the Era of Data-Centric AI 2076 Design: One, but in different forms 2077 Personalized Soups: Personalized Large Language Model Alignment via Post-hocParameter Merging 2078 Learning a Recurrent Visual Representation for Image Caption Generation 2079 Simple Applications of BERT for Ad Hoc Document Retrieval 2080 Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs 2081 Peer-to-peer Federated Learning on Graphs 2082 Identifying modular flows on multilayer networks reveals highly overlappingorganization in social systems 2083 Generative Adversarial Networks recover features in astrophysical images ofgalaxies beyond the deconvolution limit 2084 How Auto-Encoders Could Provide Credit Assignment in Deep Networks via TargetPropagation 2085 Bag of Freebies for Training Object Detection Neural Networks 2086 Artificial Intelligence and Robotics 2087 Exploring Nearest Neighbor Approaches for Image Captioning 2088 Contrastive Self-supervised Sequential Recommendation with Robust Augmentation 2089 Diversity in Faces 2090 Hybrid Spectrogram and Waveform Source Separation 2091 Do GANs actually learn the distribution? An empirical study 2092 Unsupervised Domain Adaptation in Semantic Segmentation: a Review 2093 C3: Zero-shot Text-to-SQL with ChatGPT 2094 Embers of Autoregression: Understanding Large Language Models Through theProblem They are Trained to Solve 2095 Don't Unroll Adjoint: Differentiating SSA-Form Programs 2096 GraphiT: Encoding Graph Structure in Transformers 2097 Early Detection of Breast Cancer using SVM Classifier Technique 2098 Attempto Controlled English (ACE) 2099 Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals 2100 Research Agenda in Cloud Technologies 2101 Subjective and Objective Quality Assessment of Image: A Survey 2102 Unsupervised Predictive Memory in a Goal-Directed Agent 2103 Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using RawWaveforms 2104 Towards the Automatic Anime Characters Creation with Generative AdversarialNetworks 2105 RecSim: A Configurable Simulation Platform for Recommender Systems 2106 Pretraining is All You Need for Image-to-Image Translation 2107 The Statistical Complexity of Interactive Decision Making 2108 Shannon Information and Kolmogorov Complexity 2109 Video Super-Resolution Transformer 2110 Parametrized Deep Q-Networks Learning: Reinforcement Learning withDiscrete-Continuous Hybrid Action Space 2111 Label Refinery: Improving ImageNet Classification through Label Progression 2112 Learning a Rotation Invariant Detector with Rotatable Bounding Box 2113 Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception 2114 L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning 2115 Understanding and Improving Transformer From a Multi-Particle Dynamic SystemPoint of View 2116 Differential Privacy-enabled Federated Learning for Sensitive Health Data 2117 Semantic Image Synthesis via Diffusion Models 2118 Leakage and the Reproducibility Crisis in ML-based Science 2119 Service Level Agreement (SLA) in Utility Computing Systems 2120 Artificial Intelligence in the Battle against Coronavirus (COVID-19): A Surveyand Future Research Directions 2121 Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-GrainedChinese Understanding 2122 Benchmarking Batch Deep Reinforcement Learning Algorithms 2123 DeeperLab: Single-Shot Image Parser 2124 Deep Learning Inference in Facebook Data Centers: Characterization, PerformanceOptimizations and Hardware Implications 2125 Bayesian Recurrent Neural Networks 2126 An Overview on Data Representation Learning: From Traditional Feature Learningto Recent Deep Learning 2127 A Differentiable Programming System to Bridge Machine Learning and ScientificComputing 2128 Exploration-Exploitation in Constrained MDPs 2129 Protein Structure and Sequence Generation with Equivariant Denoising DiffusionProbabilistic Models 2130 EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos withAudio2Video Diffusion Model under Weak Conditions 2131 DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral PlanningStates for Autonomous Driving 2132 Gryphon: An Information Flow Based Approach to Message Brokering 2133 Generative Representational Instruction Tuning 2134 Hierarchical Neural Network Generative Models for Movie Dialogues 2135 A Comparative Study of Various Routing Protocols in VANET 2136 Alignment of Language Agents 2137 Generative Adversarial Active Learning 2138 Analysis of Docker Security 2139 An Entropy-based Pruning Method for CNN Compression 2140 An Evaluation of Change Point Detection Algorithms 2141 Security Analysis of A Chaos-based Image Encryption Algorithm 2142 MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation 2143 Risks from Learned Optimization in Advanced Machine Learning Systems 2144 advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch 2145 A new family of Constitutive Artificial Neural Networks towards automated modeldiscovery 2146 An Introduction to Image Synthesis with Generative Adversarial Nets 2147 Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking 2148 Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not? 2149 Deep Learning with Lung Segmentation and Bone Shadow Exclusion Techniques forChest X-Ray Analysis of Lung Cancer 2150 Rethinking with Retrieval: Faithful Large Language Model Inference 2151 The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of PhysicalConcept Understanding 2152 StyleDrop: Text-to-Image Generation in Any Style 2153 Characterising Bias in Compressed Models 2154 Various thresholds for $\ell_1$-optimization in compressed sensing 2155 Explaining Classifiers with Causal Concept Effect (CaCE) 2156 Yelp Dataset Challenge: Review Rating Prediction 2157 Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering 2158 Large Language Models for Education: A Survey and Outlook 2159 Generalized Product of Experts for Automatic and Principled Fusion of GaussianProcess Predictions 2160 Estimates on the generalization error of Physics Informed Neural Networks(PINNs) for approximating PDEs 2161 ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment 2162 Differentiable Rendering: A Survey 2163 Graph Neural Ordinary Differential Equations 2164 Deep Neural Decision Trees 2165 MLGym: A New Framework and Benchmark for Advancing AI Research Agents 2166 3D Gaussian Splatting for Real-Time Radiance Field Rendering 2167 Why Language Models Hallucinate 2168 A combination chaotic system and application in color image encryption 2169 From neural PCA to deep unsupervised learning 2170 Model evaluation for extreme risks 2171 Metaverse Shape of Your Life for Future: A bibliometric snapshot 2172 Minimax Rates of Community Detection in Stochastic Block Models 2173 TripoSR: Fast 3D Object Reconstruction from a Single Image 2174 ECG Feature Extraction Techniques - A Survey Approach 2175 Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs 2176 Residual Policy Learning 2177 Abnormality Detection and Localization in Chest X-Rays using Deep ConvolutionalNeural Networks 2178 Self-supervised Learning on Graphs: Deep Insights and New Direction 2179 Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning LargeLanguage Models 2180 Variational Option Discovery Algorithms 2181 ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning 2182 A Dissection of Overfitting and Generalization in Continuous ReinforcementLearning 2183 Comparison of non-linear activation functions for deep neural networks on MNISTclassification task 2184 Learning to Generate Images of Outdoor Scenes from Attributes and SemanticLayouts 2185 CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models 2186 A Survey of Word Embeddings Evaluation Methods 2187 On Physical Adversarial Patches for Object Detection 2188 Diagonal Based Feature Extraction for Handwritten Alphabets Recognition Systemusing Neural Network 2189 Clique Graphs and Overlapping Communities 2190 3DGen: Triplane Latent Diffusion for Textured Mesh Generation 2191 A Richly Annotated Dataset for Pedestrian Attribute Recognition 2192 Unrolled Optimization with Deep Priors 2193 Literature survey on low rank approximation of matrices 2194 Mobility Changes in Response to COVID-19 2195 Recent Advances in Algorithmic High-Dimensional Robust Statistics 2196 Yara Parser: A Fast and Accurate Dependency Parser 2197 Compressed Sensing with Deep Image Prior and Learned Regularization 2198 Connecting Generative Adversarial Networks and Actor-Critic Methods 2199 GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection 2200 DocLLM: A layout-aware generative language model for multimodal documentunderstanding 2201 Evaluating ChatGPT's Information Extraction Capabilities: An Assessment ofPerformance, Explainability, Calibration, and Faithful 2202 PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model 2203 dna2vec: Consistent vector representations of variable-length k-mers 2204 Multi-Agent Collaboration Mechanisms: A Survey of LLMs 2205 Achieving Fairness through Adversarial Learning: an Application to RecidivismPrediction 2206 Entailment as Few-Shot Learner 2207 GaussianShader: 3D Gaussian Splatting with Shading Functions for ReflectiveSurfaces 2208 6G White Paper on Localization and Sensing 2209 FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing inLatent Space 2210 Intelligent Approaches to interact with Machines using Hand Gesture Recognitionin Natural way: A Survey 2211 An Improved Apriori Algorithm for Association Rules 2212 Jpeg Image Compression Using Discrete Cosine Transform - A Survey 2213 A Survey of Reinforcement Learning for Large Reasoning Models 2214 LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models 2215 Improving Multi-Task Deep Neural Networks via Knowledge Distillation for NaturalLanguage Understanding 2216 Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition 2217 Quasar: Datasets for Question Answering by Search and Reading 2218 UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion ProbabilisticModels 2219 Taming VAEs 2220 Deep Model Compression: Distilling Knowledge from Noisy Teachers 2221 Robust Learning with Jacobian Regularization 2222 Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents 2223 A Survey on The Expressive Power of Graph Neural Networks 2224 A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 AllYou Need? 2225 Next-ViT: Next Generation Vision Transformer for Efficient Deployment inRealistic Industrial Scenarios 2226 Foundational Challenges in Assuring Alignment and Safety of Large LanguageModels 2227 Question Answering and Question Generation as Dual Tasks 2228 Embedding Projector: Interactive Visualization and Interpretation of Embeddings 2229 Benchmarking Detection Transfer Learning with Vision Transformers 2230 DeepArchitect: Automatically Designing and Training Deep Architectures 2231 Multi-modal Sensor Fusion for Auto Driving Perception: A Survey 2232 RouteLLM: Learning to Route LLMs with Preference Data 2233 ISIC 2017 - Skin Lesion Analysis Towards Melanoma Detection 2234 Learning Reporting Dynamics during Breaking News for Rumour Detection in SocialMedia 2235 Machine Teaching: A New Paradigm for Building Machine Learning Systems 2236 Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm withExperience Replay and Target Network 2237 Replication study: Development and validation of deep learning algorithm fordetection of diabetic retinopathy in retinal fundus 2238 Checkerboard artifact free sub-pixel convolution: A note on sub-pixelconvolution, resize convolution and convolution resize 2239 Absolute Zero: Reinforced Self-play Reasoning with Zero Data 2240 Group Lasso with Overlaps: the Latent Group Lasso approach 2241 Neural Models for Information Retrieval 2242 Unifying Graph Convolutional Neural Networks and Label Propagation 2243 The AI Index 2021 Annual Report 2244 Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box KnowledgeTransfer 2245 Between words and characters: A Brief History of Open-Vocabulary Modeling andTokenization in NLP 2246 Unified Vision and Language Prompt Learning 2247 A hybrid bat algorithm 2248 Hamiltonian Graph Networks with ODE Integrators 2249 Perception, Reason, Think, and Plan: A Survey on Large Multimodal ReasoningModels 2250 Parcels v0.9: prototyping a Lagrangian Ocean Analysis framework for thepetascale age 2251 Reconstruction and Analysis of Cancer-specific Gene Regulatory Networks fromGene Expression Profiles 2252 Brownian Functionals in Physics and Computer Science 2253 Molecule Attention Transformer 2254 On the Importance of Noise Scheduling for Diffusion Models 2255 CogVLM2: Visual Language Models for Image and Video Understanding 2256 An Overview of Machine Teaching 2257 Co-simulation: State of the art 2258 An All-in-One Network for Dehazing and Beyond 2259 LSHTC: A Benchmark for Large-Scale Text Classification 2260 A Web of Hate: Tackling Hateful Speech in Online Social Spaces 2261 Attention Interpretability Across NLP Tasks 2262 Multi-Column Deep Neural Networks for Offline Handwritten Chinese CharacterClassification 2263 Policy Learning with Observational Data 2264 The Capacity for Moral Self-Correction in Large Language Models 2265 Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model 2266 Artificial Intelligence and Life in 2030: The One Hundred Year Study onArtificial Intelligence 2267 Discriminative Active Learning 2268 Neural Network Matrix Factorization 2269 Automated Machine Learning: State-of-The-Art and Open Challenges 2270 Introduction to Queueing Theory and Stochastic Teletraffic Models 2271 iStar 2.0 Language Guide 2272 Blended learning models 2273 SDXL-Lightning: Progressive Adversarial Diffusion Distillation 2274 A Survey and Taxonomy of Graph Sampling 2275 A memristive nanoparticle/organic hybrid synapstor for neuro-inspired computing 2276 The Expando-Mono-Duo Design Pattern for Text Ranking with PretrainedSequence-to-Sequence Models 2277 Understanding SSIM 2278 Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos 2279 Scaling Nakamoto Consensus to Thousands of Transactions per Second 2280 Masked Face Recognition for Secure Authentication 2281 WideDTA: prediction of drug-target binding affinity 2282 Blended Learning or E-learning? 2283 LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling 2284 A Scalable Deep Neural Network Architecture for Multi-Building and Multi-FloorIndoor Localization Based on Wi-Fi Fingerprinting 2285 OmniSVG: A Unified Scalable Vector Graphics Generation Model 2286 Multivariate Industrial Time Series with Cyber-Attack Simulation: FaultDetection Using an LSTM-based Predictive Data Model 2287 LongLive: Real-time Interactive Long Video Generation 2288 Minimizing the Age of Information through Queues 2289 Improved Speech Enhancement with the Wave-U-Net 2290 Survey on QoE\QoS Correlation Models For Multimedia Services 2291 Jailbreak Attacks and Defenses Against Large Language Models: A Survey 2292 Neural Machine Translation and Sequence-to-sequence Models: A Tutorial 2293 Deep Reinforcement Learning for Sepsis Treatment 2294 FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving FederatedLearning 2295 CodeGemma: Open Code Models Based on Gemma 2296 Automatic Anomaly Detection in the Cloud Via Statistical Learning 2297 True to the Model or True to the Data? 2298 Data-centric Misbehavior Detection in VANETs 2299 CAFE: Catastrophic Data Leakage in Vertical Federated Learning 2300 Gotta Learn Fast: A New Benchmark for Generalization in RL 2301 Real or Fake? Learning to Discriminate Machine from Human Generated Text 2302 Deep Learning in Finance 2303 Comparison of different Methods for Univariate Time Series Imputation in R 2304 Convex recovery of a structured signal from independent random linearmeasurements 2305 A Review of Sparse Expert Models in Deep Learning 2306 Learning Neural Causal Models from Unknown Interventions 2307 Large Language Models for Robotics: A Survey 2308 Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning 2309 End-to-End Deep Reinforcement Learning for Lane Keeping Assist 2310 Deep Learning on FPGAs: Past, Present, and Future 2311 Best-first Model Merging for Hidden Markov Model Induction 2312 Scalable Zero-shot Entity Linking with Dense Entity Retrieval 2313 Improving Variational Auto-Encoders using Householder Flow 2314 Randomized sketches for kernels: Fast and optimal non-parametric regression 2315 qHiPSTER: The Quantum High Performance Software Testing Environment 2316 Automated software vulnerability detection with machine learning 2317 Neural Embeddings of Graphs in Hyperbolic Space 2318 Interactive Visualization of 2-D Persistence Modules 2319 Automated Design of Deep Learning Methods for Biomedical Image Segmentation 2320 Indoor occupancy estimation from carbon dioxide concentration 2321 Neural Architecture Search: Insights from 1000 Papers 2322 Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs 2323 ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turnComparisons 2324 Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3DUnderstanding, Generation, and Instruction Following 2325 White Paper on Critical and Massive Machine Type Communication Towards 6G 2326 MODULAR: Software for the Autonomous Computation of Modularity in Large NetworkSets 2327 Music transcription modelling and composition using deep learning 2328 Interpreting Blackbox Models via Model Extraction 2329 Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks 2330 The multi-armed bandit problem with covariates 2331 LightLDA: Big Topic Models on Modest Compute Clusters 2332 An Overview of Melanoma Detection in Dermoscopy Images Using Image Processingand Machine Learning 2333 Agent AI: Surveying the Horizons of Multimodal Interaction 2334 OS-ATLAS: A Foundation Action Model for Generalist GUI Agents 2335 A Neural Network based Approach for Predicting Customer Churn in CellularNetwork Services 2336 Chaotic multi-objective optimization based design of fractional order PIλDμcontroller in AVR system 2337 Differential Transformer 2338 Real-time Traffic Accident Risk Prediction based on Frequent Pattern Tree 2339 A Deep-Reinforcement Learning Approach for Software-Defined Networking RoutingOptimization 2340 Practical Deep Reinforcement Learning Approach for Stock Trading 2341 Early Visual Concept Learning with Unsupervised Deep Learning 2342 Transformer for Graphs: An Overview from Architecture Perspective 2343 Interpretable to Whom? A Role-based Model for Analyzing Interpretable MachineLearning Systems 2344 IBM Federated Learning: an Enterprise Framework White Paper V0.1 2345 V-STaR: Training Verifiers for Self-Taught Reasoners 2346 PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors 2347 TALM: Tool Augmented Language Models 2348 On the Generalization of SFT: A Reinforcement Learning Perspective with RewardRectification 2349 Spatial Broadcast Decoder: A Simple Architecture for Learning DisentangledRepresentations in VAEs 2350 Deep Reinforcement Learning for List-wise Recommendations 2351 FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age 2352 Detection of Cyberbullying Incidents on the Instagram Social Network 2353 Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive EffectiveReinforcement Learning for LLM Reasoning 2354 YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles 2355 Defeating Image Obfuscation with Deep Learning 2356 Random feedback weights support learning in deep neural networks 2357 Parsing Inside-Out 2358 A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition,Speaker Verification and Spoken Language Understanding 2359 VAFL: a Method of Vertical Asynchronous Federated Learning 2360 Recommender System for Online Dating Service 2361 Transforming Question Answering Datasets Into Natural Language InferenceDatasets 2362 A Survey of Label-noise Representation Learning: Past, Present and Future 2363 Max-Margin Object Detection 2364 CoPhIR: a Test Collection for Content-Based Image Retrieval 2365 Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using QuantitativeFeatures from Chest CT Images 2366 Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware DirectPreference Optimization 2367 Distributed Deep Learning Using Synchronous Stochastic Gradient Descent 2368 Optimization for deep learning: theory and algorithms 2369 Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study 2370 Graph Partitioning using Quantum Annealing on the D-Wave System 2371 Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping 2372 HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec 2373 IndicTrans2: Towards High-Quality and Accessible Machine Translation Models forall 22 Scheduled Indian Languages 2374 Naive Bayes and Text Classification I - Introduction and Theory 2375 CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent PixelSynthesis 2376 First Analysis of Local GD on Heterogeneous Data 2377 Support recovery without incoherence: A case for nonconvex regularization 2378 HEPData: a repository for high energy physics data 2379 A comparison of LSTM and GRU networks for learning symbolic sequences 2380 Path Selection for Quantum Repeater Networks 2381 Equinox: neural networks in JAX via callable PyTrees and filteredtransformations 2382 Don't forget, there is more than forgetting: new metrics for Continual Learning 2383 PFLD: A Practical Facial Landmark Detector 2384 Scalable and Transferable Black-Box Jailbreaks for Language Models via PersonaModulation 2385 Good Colour Maps: How to Design Them 2386 Sociotechnical Safety Evaluation of Generative AI Systems 2387 TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption 2388 Deep Deterministic Policy Gradient for Urban Traffic Light Control 2389 Griffin: Mixing Gated Linear Recurrences with Local Attention for EfficientLanguage Models 2390 A Modern Take on the Bias-Variance Tradeoff in Neural Networks 2391 Quantum Software Engineering: Landscapes and Horizons 2392 IPOD: Intensive Point-based Object Detector for Point Cloud 2393 DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approachfor Computer-Aided Diagnosis Systems 2394 Provable Inductive Matrix Completion 2395 Phase-Remapping Attack in Practical Quantum Key Distribution Systems 2396 Alzheimer's Disease Diagnostics by a Deeply Supervised Adaptable 3DConvolutional Network 2397 ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine LearningModel for Detecting Short ChatGPT-generated Text 2398 Energy Distribution of EEG Signals: EEG Signal Wavelet-Neural Network Classifier 2399 SPP-Net: Deep Absolute Pose Regression with Synthetic Views 2400 NAM: Normalization-based Attention Module 2401 Notes on Kullback-Leibler Divergence and Likelihood 2402 Local Differential Privacy and Its Applications: A Comprehensive Survey 2403 The Robust Manifold Defense: Adversarial Training using Generative Models 2404 Deep Reinforcement Learning for Autonomous Driving 2405 A Bayesian approach for predicting the popularity of tweets 2406 Consciousness in Artificial Intelligence: Insights from the Science ofConsciousness 2407 VIOLA: Imitation Learning for Vision-Based Manipulation with Object ProposalPriors 2408 LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory ofTransformers 2409 Image Encryption Using Differential Evolution Approach in Frequency Domain 2410 OTTER 3.3 Reference Manual 2411 Rectified Flow: A Marginal Preserving Approach to Optimal Transport 2412 sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In NeuralWord Embeddings 2413 A User Simulator for Task-Completion Dialogues 2414 MolecularRNN: Generating realistic molecular graphs with optimized properties 2415 Predicting Financial Markets: Comparing Survey, News, Twitter and Search EngineData 2416 Silent Data Corruptions at Scale 2417 Variational Federated Multi-Task Learning 2418 Training Vision Transformers for Image Retrieval 2419 Federated Learning Of Out-Of-Vocabulary Words 2420 Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting 2421 FP8 Formats for Deep Learning 2422 Tracking Social Media Discourse About the COVID-19 Pandemic: Development of aPublic Coronavirus Twitter Data Set 2423 A Random Matrix Approach to Neural Networks 2424 ExpertPrompting: Instructing Large Language Models to be Distinguished Experts 2425 What Trends in Chinese Social Media 2426 LiDAR-Camera Calibration using 3D-3D Point correspondences 2427 Emerging Properties in Unified Multimodal Pretraining 2428 Foveation-based Mechanisms Alleviate Adversarial Examples 2429 Active Libraries: Rethinking the roles of compilers and libraries 2430 Interlaced Sparse Self-Attention for Semantic Segmentation 2431 Satellite Imagery Feature Detection using Deep Convolutional Neural Network: AKaggle Competition 2432 Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural NetworkMethod 2433 On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses 2434 Memory Bounded Deep Convolutional Networks 2435 GenCast: Diffusion-based ensemble forecasting for medium-range weather 2436 Transformer Explainer: Interactive Learning of Text-Generative Models 2437 Retentive Network: A Successor to Transformer for Large Language Models 2438 Bayesian Network Constraint-Based Structure Learning Algorithms: Parallel andOptimised Implementations in the bnlearn R Package 2439 A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability 2440 An Architecture Combining Convolutional Neural Network (CNN) and Support VectorMachine (SVM) for Image Classification 2441 Monkeypox Skin Lesion Detection Using Deep Learning Models: A Feasibility Study 2442 LiveCap: Real-time Human Performance Capture from Monocular Video 2443 Latent Multi-task Architecture Learning 2444 Logical Neural Networks 2445 An Analysis of Neural Language Modeling at Multiple Scales 2446 Density-aware Chamfer Distance as a Comprehensive Metric for Point CloudCompletion 2447 AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs HallucinationEvaluation 2448 Combining GHOST and Casper 2449 SciFive: a text-to-text transformer model for biomedical literature 2450 Data Mining Applications: A comparative Study for Predicting Student'sperformance 2451 Transformers with convolutional context for ASR 2452 A New Era in Citation and Bibliometric Analyses: Web of Science, Scopus, andGoogle Scholar 2453 AI-Generated Content (AIGC): A Survey 2454 MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use 2455 Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models 2456 A Physics-Guided Neural Network Framework for Elastic Plates: Comparison ofGoverning Equations-Based and Energy-Based Approaches 2457 Transformers without Normalization 2458 Survey on Security Issues in Cloud Computing and Associated MitigationTechniques 2459 ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using LargeLanguage Models 2460 A Software Methodology for Compiling Quantum Programs 2461 Impact of Pretraining Term Frequencies on Few-Shot Reasoning 2462 Towards Automated Deep Learning: Efficient Joint Neural Architecture andHyperparameter Search 2463 LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models 2464 Longitudinal Analysis of Android Ad Library Permissions 2465 Efficient Pipeline for Camera Trap Image Review 2466 Microstructure Representation and Reconstruction of Heterogeneous Materials viaDeep Belief Network for Computational Material De 2467 Dictionary Identification - Sparse Matrix-Factorisation via$\ell_1$-Minimisation 2468 F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models 2469 Artificial Ant Colonies in Digital Image Habitats - A Mass Behaviour EffectStudy on Pattern Recognition 2470 Improvements of real coded genetic algorithms based on differential operatorspreventing premature convergence 2471 The Community Authorization Service: Status and Future 2472 Stereo Correspondence and Reconstruction of Endoscopic Data Challenge 2473 Memory-Efficient Implementation of DenseNets 2474 An Evaluation of the Human-Interpretability of Explanation 2475 First-Pass Large Vocabulary Continuous Speech Recognition using Bi-DirectionalRecurrent DNNs 2476 Evaluation of Retrieval-Augmented Generation: A Survey 2477 Bridging Category-level and Instance-level Semantic Image Segmentation 2478 Camera identification with deep convolutional networks 2479 Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches thePerformance of Expert-developed QSAR/QSPR Models 2480 Distilled One-Shot Federated Learning 2481 CNN-based Density Estimation and Crowd Counting: A Survey 2482 No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation 2483 Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework forAssimilating Flow Visualization Data 2484 Self-Supervised Learning for Stereo Matching with Self-Improving Ability 2485 VinVL: Revisiting Visual Representations in Vision-Language Models 2486 A Survey of Large Language Models in Medicine: Progress, Application, andChallenge 2487 Optimizing Variational Quantum Algorithms using Pontryagin's Minimum Principle 2488 Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with InfiniteLength 2489 Video-R1: Reinforcing Video Reasoning in MLLMs 2490 Datamodels: Predicting Predictions from Training Data 2491 A Study on Feature Selection Techniques in Educational Data Mining 2492 Advancing LLM Reasoning Generalists with Preference Trees 2493 R-CNNs for Pose Estimation and Action Detection 2494 A Long Short-Term Memory Recurrent Neural Network Framework for Network TrafficMatrix Prediction 2495 Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-LanguagePlanning 2496 R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wiseGroup Relative Policy Optimization 2497 LipNet: End-to-End Sentence-level Lipreading 2498 Adapting Auxiliary Losses Using Gradient Similarity 2499 A Survey on Contextual Embeddings 2500 O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning 2501 AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding 2502 Qwen2.5-Omni Technical Report 2503 A NURBS-based Inverse Analysis for Reconstruction of Nonlinear Deformations ofThin Shell Structures 2504 Translating Natural Language to Planning Goals with Large-Language Models 2505 RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots 2506 Computer-aided molecular design: An introduction and review of tools,applications, and solution techniques 2507 Audio Spectrogram Representations for Processing with Convolutional NeuralNetworks 2508 Learning from Failure: Training Debiased Classifier from Biased Classifier 2509 Reinforcement Learning Neural Turing Machines - Revised 2510 Places205-VGGNet Models for Scene Recognition 2511 Continual Learning via Neural Pruning 2512 Sequence-to-Sequence RNNs for Text Summarization 2513 Coresets and Sketches 2514 Overfitting Mechanism and Avoidance in Deep Neural Networks 2515 Multi-Objective Deep Reinforcement Learning 2516 Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual SoftmaxLoss 2517 Combining Independent Modules to Solve Multiple-choice Synonym and AnalogyProblems 2518 Video Object Segmentation and Tracking: A Survey 2519 A Deadline and Budget Constrained Cost-Time Optimisation Algorithm forScheduling Task Farming Applications on Global Grids 2520 Near-Optimal Algorithms for Differentially-Private Principal Components 2521 Learning to be Safe: Deep RL with a Safety Critic 2522 Native Sparse Attention: Hardware-Aligned and Natively Trainable SparseAttention 2523 Extending the OpenAI Gym for robotics: a toolkit for reinforcement learningusing ROS and Gazebo 2524 SANA: Efficient High-Resolution Image Synthesis with Linear DiffusionTransformers 2525 Common Limitations of Image Processing Metrics: A Picture Story 2526 A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework forInformation Retrieval Techniques 2527 Stochastic Semantics and Statistical Model Checking for Networks of Priced TimedAutomata 2528 Star-galaxy Classification Using Deep Convolutional Neural Networks 2529 Measuring Progress on Scalable Oversight for Large Language Models 2530 The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation 2531 TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation 2532 Maintaining cooperation in complex social dilemmas using deep reinforcementlearning 2533 B-CNN: Branch Convolutional Neural Network for Hierarchical Classification 2534 Few-Shot Learning with Metric-Agnostic Conditional Embeddings 2535 HoloLens 2 Research Mode as a Tool for Computer Vision Research 2536 HNHN: Hypergraph Networks with Hyperedge Neurons 2537 Rethinking CNN Models for Audio Classification 2538 Towards Large Reasoning Models: A Survey of Reinforced Reasoning with LargeLanguage Models 2539 InternLM-XComposer-2.5: A Versatile Large Vision Language Model SupportingLong-Contextual Input and Output 2540 mHC: Manifold-Constrained Hyper-Connections 2541 Can neural machine translation do simultaneous translation? 2542 Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering 2543 Diverse mini-batch Active Learning 2544 Algorithms, Initializations, and Convergence for the Nonnegative MatrixFactorization 2545 Convergence Analysis for Rectangular Matrix Completion Using Burer-MonteiroFactorization and Gradient Descent 2546 An Implementation of Faster RCNN with Study for Region Sampling 2547 Kling-Omni Technical Report 2548 DeepID-Net: multi-stage and deformable deep convolutional neural networks forobject detection 2549 Playground v2.5: Three Insights towards Enhancing Aesthetic Quality inText-to-Image Generation 2550 Simple and Controllable Music Generation 2551 Rethinking the Trigger of Backdoor Attack 2552 On-Device Machine Learning: An Algorithms and Learning Theory Perspective 2553 Are Large-scale Datasets Necessary for Self-Supervised Pre-training? 2554 Survey of Dropout Methods for Deep Neural Networks 2555 A Survey on Honeypot Software and Data Analysis 2556 Gated Transformer Networks for Multivariate Time Series Classification 2557 Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans 2558 LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-StageRule-Based RL 2559 DreamGaussian4D: Generative 4D Gaussian Splatting 2560 Resiliency of Deep Neural Networks under Quantization 2561 Split Learning for collaborative deep learning in healthcare {{ $json.postContent }} Top comments (0) Code of Conduct • Report abuse
Top comments (0)