北京通用人工智能研究院BIGAI

科研成果

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

STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning

Heterogeneous Value Alignment Evaluation for Large Language Models

ProAgent: Building Proactive Cooperative Agents with Large Language Models

RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking

Weakly Supervised Video Moment Localization with Contrastive Negative Sample Mining