Chenhui Li

representation learning (1) vision transformer (1) causal reasoning (1) feature extraction (1) direct preference optimization (1) self-supervised learning (1) attention mechanism (1) visual object tracking (1) multimodal learning (1) multi-label classification (1) text representation (1) audio-visual learning (1) 3d scene understanding (1) instance segmentation (1) open-vocabulary recognition (1) feature representation (1) visual tracking (1) normalizing flow (1) vision-language model (1) retrieval augmented generation (1)