北京通用人工智能研究院BIGAI

科研成果

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

Shu ̄o Wén Jiˇe Zì: Rethinking Dictionaries and Glyphs for Chinese Language Pre-training

In situ bidirectional human-robot value alignment

SHARP: Search-Based Adversarial Attack for Structured Prediction

Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships