Ding Zhao

Associate Professor@Carnegie Mellon University·美国·OpenReview

研究方向

trustworthy AI · reinforcement learning · safe RL · robust RL · rare event simulation · Bayesian nonparametric · Optimal transport · Meta learning · AI Safety

6.0

合作者 (20)

Ding Zhao

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels

SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs

Tailored Primitive Initialization is the Secret Key to Reinforcement Learning

Learning to Interact in World Latent for Team Coordination

Behavior Injection: Preparing Language Models for Reinforcement Learning

Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving