Junjie Ke

diffusion model (2) vision-language model (2) reward model (2) neural network training (1) model robustness (1) knowledge distillation (1) domain generalization (1) preference optimization (1) multimodal learning (1) adversarial augmentation (1) neural architecture search (1) visual reasoning (1) text-to-image generation (1) reinforcement learning from human feedback (1) optical computing (1) iterative refinement (1) human feedback (1) in-context learning (1) convolutional neural network (1) image generation (1)