慣性聚合 高效追蹤和閱讀你感興趣的部落格、新聞、科技資訊
閱讀原文 在慣性聚合中打開

推薦訂閱源

D
Docker
月光博客
月光博客
T
The Blog of Author Tim Ferriss
博客园 - 【当耐特】
量子位
V
Visual Studio Blog
Last Week in AI
Last Week in AI
A
About on SuperTechFans
Google DeepMind News
Google DeepMind News
李成银的技术随笔
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
The Cloudflare Blog
Microsoft Azure Blog
Microsoft Azure Blog
Stack Overflow Blog
Stack Overflow Blog
Apple Machine Learning Research
Apple Machine Learning Research
The GitHub Blog
The GitHub Blog
Engineering at Meta
Engineering at Meta
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
MongoDB | Blog
MongoDB | Blog
雷峰网
雷峰网

cs.LG updates on arXiv.org

Personalized Generative Models for Contextual Debiasing From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control Amortized Factor Inference Networks for Posterior Inference Classification and detection of multiple UAVs using rational Gaussian wavelet neural networks Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning Modeling Dynamic Mixtures of Time-Delay Systems from Streaming Time Series AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion Neural Bayesian Sequential Routing GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks Function-Valued Causal Influence in Nonlinear Time Series The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works Balancing Plasticity and Stability with Fast and Slow Successor Features InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization FM-fMRI: Event Conditioned Flow Matching for Rest-to-Task fMRI Time-Series Synthesis TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach CSV-ViT: A Vision Transformer with the Variable-sized Cortical Supervertices for Detection of Alzheimer's Disease Pathologies Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback Curriculum Learning for Safety Alignment A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks GEM: Geometric Entropy Mixing for Optimal LLM Data Curation Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage Unified Neural Scaling Laws Semigroup Consistency as a Diagnostic for Learned Physics Simulators QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular Carcinoma Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection Co-folding model guided by structural proteomics Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention Stateful Inference for Low-Latency Multi-Agent Tool Calling Two-Parameter Flows for Learning Population Dynamics of Physical Systems On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series A Fast and Generic Energy-Shifting Transformer for Hybrid Monte Carlo Radiotherapy Calculation ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding
世界模型可識別標籤對應
Youngin Kim · 2026-05-19 · via cs.LG updates on arXiv.org

檢視 PDF HTML (實驗性)

摘要:基於Token的變換器世界模型在視覺強化學習中展現出強大的性能,但通常在長視野展開中存在時間不一致性,包括物體重複、消失和轉變。一個關鍵原因是大多數現有方法將下一幀預測純粹視為Token生成問題,而沒有考慮Token在時間上的持久性。我們介紹了可識別Token對應(ITC),這是一個針對基於Token的變換器世界模型的解碼步驟,將下一幀預測制定為一個具有潛在Token對應變量的結構化分配問題:每個下一幀的Token都是由複製前一幀的Token或生成一個新Token來解釋。ITC不變更變換器架構和訓練程序,並可以加在現有主幹上。我們的實驗在4個挑戰基準測試中顯示出最先進的性能。所提出的方法在Craftax-classic基準測試中達到72.5%的回報和35.6%的得分,顯著超過了之前的最佳結果67.4%和27.9%。我們釋放了我们的源代码在此 https URL
主題: 機器學習 (cs.LG);人工智慧 (cs.AI);電腦視覺與模式識別 (cs.CV)
引用格式: arXiv:2605.16457 [cs.LG]
  (或 arXiv:2605.16457v3 [cs.LG] 對此版本)
  https://doi.org/10.48550/arXiv.2605.16457

arXiv發行的DOI透過DataCite

提交通過歷史

来自:Youngin Kim [查看郵件]
[v1] 五月十五日,2026年 上午05:58:58 UTC (1,722 KB)
[v2] 五月廿一,2026年 00:53:36 UTC (1,675 KB)
[v3] 五月廿六,2026年 03:24:15 UTC (1,675 KB)