北京通用人工智能研究院BIGAI

科研成果

LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments

Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels

Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling

LooGLE: Can Long-Context Language Models Understand Long Contexts?

Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field

VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions