北京通用人工智能研究院BIGAI

科研成果

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

All-in-one 3D Scene Synthesis with an Extensible and Self-Reflective Agent

Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Social World Model-Augmented Mechanism Design Policy Learning

NEP: Autoregressive lmage Editing via Next EditingToken Prediction