Yuanyang Yin

feature alignment (1) transformer architecture (1) hyperparameter optimization (1) video generation (1) multimodal learning (1) scaling law (1) vision-language model (1) multimodal large language model (1) model scaling (1) embedding alignment (1) large vision-language model (1) vision encoder (1) video diffusion (1) video diffusion model (1) diffusion transformer (1) adapter architecture (1) vision-language integration (1) compute budget (1) model size (1) cross-modal understanding (1)