OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
Paper • 2503.17352 • Published • 24
VLM RL Reasoning
-
-
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
Paper • 2503.16660 • Published • 72 -
CoMP: Continual Multimodal Pre-training for Vision Foundation Models
Paper • 2503.18931 • Published • 30 -
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
Paper • 2503.13964 • Published • 20 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 172 -
ViLBench: A Suite for Vision-Language Process Reward Modeling
Paper • 2503.20271 • Published • 7 -
Video-R1: Reinforcing Video Reasoning in MLLMs
Paper • 2503.21776 • Published • 79 -
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Paper • 2504.02587 • Published • 32 -
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
Paper • 2504.07934 • Published • 21 -
Efficient Medical VIE via Reinforcement Learning
Paper • 2506.13363 • Published • 31 -
Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?
Paper • 2506.17417 • Published • 11