北京通用人工智能研究院BIGAI

科研成果

MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control

TarGF: Learning Target Gradient Field for Object Rearrangement

EgoTaskQA: Understanding Human Tasks in Egocentric Videos

HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes

On the Learning Mechanisms in Physical Reasoning

Decoupling the Depth and Scope of Graph Neural Networks