Victor Shea-Jay Huang

diffusion transformer (2) transformer architecture (1) image generation (1) hyperparameter optimization (1) video generation (1) multimodal learning (1) scaling law (1) vision-language model (1) supervised fine-tuning (1) multimodal large language model (1) sparse autoencoder (1) model scaling (1) large vision-language model (1) vision encoder (1) safety benchmark (1) video diffusion (1) video diffusion model (1) multi-image reasoning (1) attack success rate (1) reasoning process (1)