惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Forbes - Security
Forbes - Security
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
P
Palo Alto Networks Blog
Martin Fowler
Martin Fowler
T
Threatpost
D
Docker
S
Schneier on Security
M
MIT News - Artificial intelligence
G
Google Developers Blog
L
LINUX DO - 热门话题
J
Java Code Geeks
月光博客
月光博客
博
博客园 - 三生石上(FineUI控件)
IT之家
IT之家
博
博客园 - Franky
C
Cyber Attacks, Cyber Crime and Cyber Security
K
Kaspersky official blog
Google DeepMind News
Google DeepMind News
N
News and Events Feed by Topic
V
Vulnerabilities – Threatpost
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
人人都是产品经理
人人都是产品经理
Spread Privacy
Spread Privacy
T
Tailwind CSS Blog
爱范儿
爱范儿
阮一峰的网络日志
阮一峰的网络日志
U
Unit 42
C
CERT Recently Published Vulnerability Notes
The GitHub Blog
The GitHub Blog
Simon Willison's Weblog
Simon Willison's Weblog
NISL@THU
NISL@THU
MongoDB | Blog
MongoDB | Blog
Application and Cybersecurity Blog
Application and Cybersecurity Blog
H
Heimdal Security Blog
Recorded Future
Recorded Future
云风的 BLOG
云风的 BLOG
SecWiki News
SecWiki News
P
Privacy International News Feed
P
Proofpoint News Feed
O
OpenAI News
B
Blog
腾
腾讯CDC
F
Full Disclosure
Apple Machine Learning Research
Apple Machine Learning Research
T
Tor Project blog
H
Hacker News: Front Page
Project Zero
Project Zero
Hugging Face - Blog
Hugging Face - Blog
C
Cisco Blogs
S
Security Affairs

cs.CV updates on arXiv.org

ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents On the Robustness of Watermarking for Autoregressive Image Generation Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference Anthropogenic Regional Adaptation in Multimodal Vision-Language Model From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-Tuning Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance Retinal Cyst Detection from Optical Coherence Tomography Images LoViF 2026 The First Challenge on Weather Removal in Videos STORM: End-to-End Referring Multi-Object Tracking in Videos Data-Efficient Surgical Phase Segmentation in Small-Incision Cataract Surgery: A Controlled Study of Vision Foundation Models Rethinking the Diffusion Model from a Langevin Perspective Zero-shot World Models Are Developmentally Efficient Learners Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation Degradation-Consistent Paired Training for Robust AI-Generated Image Detection FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer Demographic and Linguistic Bias Evaluation in Omnimodal Language Models FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation Cross-Cultural Value Awareness in Large Vision-Language Models I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension From UAV Imagery to Agronomic Reasoning: A Multimodal LLM Benchmark for Plant Phenotyping Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception Genie 4D: Semantic-Prior-Guided 4D Dynamic Scene Reconstruction Efficient Personalization of Generative User Interfaces Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories PhysInOne: Visual Physics Learning and Reasoning in One Suite Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation Neural Distribution Prior for LiDAR Out-of-Distribution Detection Adding Another Dimension to Image-based Animal Detection Long-SCOPE: Fully Sparse Long-Range Cooperative 3D Perception CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation FIRE-CIR: Fine-grained Reasoning for Composed Fashion Image Retrieval Detecting Diffusion-generated Images via Dynamic Assembly Forests Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion Dynamic Class-Aware Active Learning for Unbiased Satellite Image Segmentation Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS) MedFormer-UR: Uncertainty-Routed Transformer for Medical Image Classification BIAS: A Biologically Inspired Algorithm for Video Saliency Detection DeFakeQ: Enabling Real-Time Deepfake Detection on Edge Devices via Adaptive Bidirectional Quantization Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning SenBen: Sensitive Scene Graphs for Explainable Content Moderation Towards Responsible Multimodal Medical Reasoning via Context-Aligned Vision-Language Models R2G: A Multi-View Circuit Graph Benchmark Suite from RTL to GDSII State Space Models are Effective Sign Language Learners: Exploiting Phonological Compositionality for Vocabulary-Scale Recognition Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup Unified Multimodal Uncertain Inference Unsupervised Local Plasticity in a Multi-Frequency VisNet Hierarchy EfficientSign: An Attention-Enhanced Lightweight Architecture for Indian Sign Language Recognition InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding On Semiotic-Grounded Interpretive Evaluation of Generative Art Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction Needle in a Haystack: One-Class Representation Learning for Detecting Rare Malignant Cells in Computational Cytology A Semi-Automated Framework for 3D Reconstruction of Medieval Manuscript Miniatures Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach Orthogonal Quadratic Complements for Vision Transformer Feed-Forward Networks HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search Assessing Privacy Preservation and Utility in Online Vision-Language Models R3PM-Net: Real-time, Robust, Real-world Point Matching Network Tipiano: Cascaded Piano Hand Motion Synthesis via Fingertip Priors Belief-Aware VLM Model for Human-like Reasoning GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents B-MoE: A Body-Part-Aware Mixture-of-Experts "All Parts Matter" Approach to Micro-Action Recognition FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention BiCLIP: Domain Canonicalization via Structured Geometric Transformation Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers When & How to Write for Personalized Demand-aware Query Rewriting in Video Search Relational Visual Similarity Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models OmniPrism: Learning Disentangled Visual Concept for Image Generation MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions
Latent Visual States for Efficient Multimodal Reasoning
[Submitted on 23 Jun 2026] · 2026-06-24 · via cs.CV updates on arXiv.org

View PDF HTML (experimental)

Abstract:The integration of visual evidence has significantly enhanced the capabilities of large multimodal models. However, this integration predominantly relies on generating discrete outputs (etc., code or box coordinates) to invoke external tools, a process that introduces rigid dependencies and substantial latency. To overcome these limitations, we propose {EVA} (LatEnt Visual StAtes), a novel framework that natively generates continuous latent visual representations. These internal representations manifest as an adaptive sequence of Latent\_slot tokens, serving as intermediate visual thoughts during the reasoning process. These Latent\_slot tokens are then trained end-to-end with the discrete text tokens. This co-optimization, notably, causes extreme policy deviation in the 'transition window' following the Latent\_slot tokens. We develop D-GSPO (Decouple-GSPO) to target this root cause by decoupling the optimization of latent and discrete components. To support SFT, we construct EVA-230K, a high-quality text-image interleaved CoT dataset encompassing a diverse range of real-world scenes, documents, charts and OCR tasks. Extensive experiments across multiple benchmarks confirm that EVA achieves significant performance gains while enhancing inference efficiency.

Submission history

From: Xiuwei Chen [view email]
[v1] Tue, 23 Jun 2026 07:22:22 UTC (2,771 KB)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。