AI & ML interests

None defined yet.

Recent Activity

DAMO-NLP-SG 's collections 7

VideoLLaMA3
Frontier Multimodal Foundation Models for Video Understanding
SSTuning
Zero-shot text classification models trained with self-supervised tuning (SSTuning)
VideoLLaMA3
Frontier Multimodal Foundation Models for Video Understanding
SSTuning
Zero-shot text classification models trained with self-supervised tuning (SSTuning)
VideoLLaMA2
Optimized VideoLLaMA with improved spatial-temporal modeling and better audio understanding capability