Zhou Yu

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents

Jailbreaking Jailbreaks: A Proactive Defense for LLMs

Rethinking reasoning with Masked Diffusion Models

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning

A General Framework for Inference-time Scaling and Steering of Diffusion Models