北京通用人工智能研究院BIGAI

科研成果

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events

3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds

VLGrammar: Grounded Grammar Induction of Vision and Language

YouRefIt: Embodied Reference Understanding with Language and Gesture