北京通用人工智能研究院BIGAI

科研成果

Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games

AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making

Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale