Zixin Guo

multimodal learning (3) image captioning (2) transfer learning (2) image difference captioning (2) attention mechanism (1) vision-language alignment (1) multi-modal learning (1) visual recognition (1) large multimodal model (1) zero-shot transfer (1) clip model (1) visual feature (1) adaptation training (1) vision language (1) noise detection (1) large language model (1) image difference (1) noise-robust training (1) fine-grained description (1) reinforcement learning (1)