北京通用人工智能研究院BIGAI

为机器立心
为人文赋理

In-Context Editing: Learning Knowledge from Self-Induced Distributions

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

Autonomous Character-Scene Interaction Synthesis from Text Instruction

Robust Data Clustering with Outliers via Transformed TensorLow-Rank Representation

Tac-Man: Tactile-Informed Prior-Free Manipulation of Articulated Objects

MindDial: Enhancing Conversational Agents with Theory-of Mind for Common Ground Alignment and Negotiation