Haoran Tang

multimodal large language model (2) text-video retrieval (2) video understanding (2) reinforcement learning (1) self-supervised learning (1) data augmentation (1) variational inference (1) factuality evaluation (1) energy-based model (1) feature space (1) state space exploration (1) continuous control (1) optical flow (1) intrinsic motivation (1) parameter-efficient fine-tuning (1) question answering (1) vision-language model (1) tabular reinforcement learning (1) maximum entropy (1) contrastive learning (1)