Yan Zeng

multimodal learning (4) causal discovery (3) contrastive learning (2) multi-task learning (2) foundation model (2) diffusion model (2) vision-language model (2) image generation (2) computational photography (1) transfer learning (1) 3d reconstruction (1) image restoration (1) active learning (1) policy optimization (1) self-supervised learning (1) neural network pruning (1) sequential decision making (1) video generation (1) object detection (1) motion synthesis (1)