Chongjie Zhang

Correlated Policy Optimization in Multi-Agent Subteams

Translating Flow to Policy via Hindsight Online Imitation

OPRIDE: Efficient Offline Preference-based Reinforcement Learning via In-Dataset Exploration

Unified Latent Steering and Residual Refinement for Online Improvement of Diffusion Policy Models

A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning

Episodic Novelty Through Temporal Distance

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving

Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset

Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective

Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks

Less is More: Exploiting Feature Density for Enhanced Membership Inference Attacks

Enhancing Decision-Making of Large Language Models via Actor-Critic

Fewer Questions, Better Answers: Efficient Offline Preference-based Reinforcement Learning via In-Dataset Exploration

Enhancing Decision-Making of Large Language Models via Actor-Critic

Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks