北京通用人工智能研究院BIGAI

科研成果

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

VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update