Shengbang Tong

Core AI (1)

multimodal learning (5) representation learning (4) self-supervised learning (4) large language model (3) vision-language model (3) vision language model (3) multimodal large language model (3) visual representation learning (3) contrastive learning (3) token compression (2) sparse rate reduction (2) benchmark evaluation (2) transformer architecture (2) visual representation (2) visual reasoning (2) visual grounding (2) decision making (1) manifold learning (1) adversarial robustness (1) vision transformer (1)