Simon Sinong Zhan

SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of LLM-based Embodied Agents

Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization

Efficient Multi-Step Reinforcement Learning with Expectation-Maximization Bootstrapping

Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents

Directly Forecasting Belief for Reinforcement Learning with Delays

Model-Enhanced Adversarial Inverse Reinforcement Learning with Model Estimation Reward Shaping in Stochastic Environments