Haiyang Xu

Techniques (1)

multimodal learning (7) multimodal large language model (6) vision-language pre-training (4) large language model (4) vision-language model (3) contrastive learning (3) in-context learning (3) image captioning (3) vision-language pretraining (3) end-to-end learning (2) diffusion model (2) large multimodal model (2) cross-modal alignment (2) foundation model (2) cross-modal learning (2) document understanding (2) adversarial training (2) visual question answering (2) 3d reconstruction (2) vision transformer (2)