Jiarui Yao

GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving

Why is Your Language Model a Poor Implicit Reward Model?

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL