Fu Feng

model initialization (3) knowledge distillation (2) diffusion model (2) model compression (2) transfer learning (1) knowledge transfer (1) text-to-image synthesis (1) text-to-image generation (1) neural network optimization (1) parameter sharing (1) weight initialization (1) zero-shot generalization (1) controllable generation (1) policy network (1) attention head (1) adaptive cluster (1) elastic scale (1) pretrained model (1) parameter-efficient adaptation (1) elastic scaling (1)