VAttnPO: Visual Attention-Guided Policy Optimization
cs.CV, cs.AI
Submitted: 2026-10-12
Updated: 2026-10-12
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- PaliGemma: A versatile 3B VLM for transfer
- StreamingClaw Technical Report
- MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
- VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- COPO: Consistency-Aware Policy Optimization
- Silkie: Preference Distillation for Large Visual Language Models
- Evaluating Object Hallucination in Large Vision-Language Models
- TempCompass: Do Video LLMs Really Understand Videos?
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
- MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
- Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning
- MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
- VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
- MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models