Sashuai Zhou

multimodal learning (2) representation learning (2) contrastive learning (2) image generation (1) reinforcement learning from human feedback (1) domain generalization (1) zero-shot learning (1) ai feedback (1) 3d vision (1) speech enhancement (1) multimodal representation (1) autoregressive model (1) foundation model (1) vision-language model (1) recommendation system (1) preference learning (1) reinforcement learning (1) open-set recognition (1) spatial reasoning (1) feature alignment (1)