Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper
•
2505.24726
•
Published
•
189
MLLM Reasoning, Rewarding, and Understanding
Papers on the reasoning, rewarding, and understanding of the MLLMs and LLMs
-
-
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
Paper • 2506.02096 • Published • 51 -
OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
Paper • 2506.02397 • Published • 35 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 120 -
Time Blindness: Why Video-Language Models Can't See What Humans Can?
Paper • 2505.24867 • Published • 75 -
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Paper • 2505.23359 • Published • 39 -
Fractured Chain-of-Thought Reasoning
Paper • 2505.12992 • Published • 21 -
MiMo-VL Technical Report
Paper • 2506.03569 • Published • 70 -
VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos
Paper • 2506.05349 • Published • 24 -
MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
Paper • 2506.05331 • Published • 12 -
How much do language models memorize?
Paper • 2505.24832 • Published • 2 -
Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
Paper • 2505.15966 • Published • 51 -
GRIT: Teaching MLLMs to Think with Images
Paper • 2505.15879 • Published • 12 -
InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning
Paper • 2505.18291 • Published • 2 -
VLM-R^3: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
Paper • 2505.16192 • Published • 10 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 35