Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper • 2511.04570 • Published 24 days ago • 204
Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning Paper • 2510.24320 • Published Oct 28 • 18
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping Paper • 2510.18927 • Published Oct 21 • 82
BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset Paper • 2507.03483 • Published Jul 4 • 23