Yu Liang

spiking neural network (3) generative reward model (2) semantic segmentation (2) reinforcement learning from human feedback (2) model compression (2) model binarization (2) diffusion model (2) image retrieval (1) domain adaptation (1) causal inference (1) multimodal learning (1) unsupervised domain adaptation (1) deep hashing (1) efficient computing (1) neural machine translation (1) collaborative learning (1) preference alignment (1) approximate nearest neighbor (1) mutual information (1) knowledge distillation (1)