Rui Liu

Adaptive Conformal Guidance for Learning under Uncertainty

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Vision-SR1: Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems