Baolin Peng

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

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

CollabLLM: From Passive Responders to Active Collaborators

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Latent Action Pretraining from Videos

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

SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models