Projects

A Streamlined Package for Minecraft AI Agent Development

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Steering Visuomotor Policy via Cross-View Goal Alignment

Master Open-World Interaction with Visual-Temporal Context Prompting

Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning

The first global synthetic dataset for physics-ML seismic wavefield modeling and full-waveform inversion