Yutong Gao

representation learning (1) contrastive learning (1) reinforcement learning (1) few-shot learning (1) policy optimization (1) image retrieval (1) token selection (1) multimodal learning (1) cross-modal learning (1) multi-modal learning (1) video understanding (1) vision language model (1) cross-modal alignment (1) prompt tuning (1) concept alignment (1) large language model (1) functional transparency (1) intrinsic interpretability (1) key frame extraction (1) representational decomposability (1)