Siyu Li

multimodal learning (2) contrastive learning (1) image retrieval (1) multilingual retrieval (1) speech processing (1) autoregressive generation (1) vision language model (1) cross-modal alignment (1) foundation model (1) multimodal large language model (1) cultural sensitivity (1) any-to-any model (1) autoregressive modeling (1) multimodal token (1) causal multimodal modeling (1) any-to-any multimodal (1) any-to-any generation (1) cross-lingual robustness (1) geopolitical bia (1) retrieval augmented generation (1)