Can Jin

Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners

Exploring the Entropy Mechanism in LLM Agents On-policy Optimization

HILDA: Hessian-Implicit Langevin with Damping and Adaptation for Diffusion Sampling

Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives

LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation

Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints