Jiafeng Liang

large language model (6) video understanding (2) vision-language model (2) multimodal learning (2) question answering (2) multi-modal large language model (2) self-supervised learning (2) video captioning (1) direct preference optimization (1) adversarial robustness (1) temporal reasoning (1) chain-of-thought reasoning (1) model distillation (1) document understanding (1) symbolic reasoning (1) scene graph generation (1) knowledge transfer (1) multi-modal learning (1) multi-view learning (1) semantic analysis (1)