Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Paper • 2506.03106 • Published Jun 3 • 6
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Paper • 2506.03106 • Published Jun 3 • 6 • 2
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs Paper • 2505.21327 • Published May 27 • 83
Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning? Paper • 2505.21374 • Published May 27 • 27
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs Paper • 2505.21327 • Published May 27 • 83
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward Paper • 2505.17018 • Published May 22 • 15
NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification Paper • 2505.16938 • Published May 22 • 119
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward Paper • 2505.17018 • Published May 22 • 15
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward Paper • 2505.17018 • Published May 22 • 15 • 2