Xinpeng Ding

large language model (2) multimodal large language model (2) 3d reconstruction (1) action recognition (1) temporal modeling (1) video segmentation (1) question answering (1) neural representation (1) multimodal learning (1) autonomous driving (1) multi-modal learning (1) video understanding (1) unsupervised domain adaptation (1) visual explanation (1) weakly-supervised learning (1) weakly supervised learning (1) implicit neural representation (1) vision language model (1) mixture of expert (1) semantic segmentation (1)