Yunke Wang

policy optimization (2) expert demonstration (2) generative adversarial imitation learning (2) reinforcement learning (2) image restoration (1) weakly supervised learning (1) policy learning (1) saliency detection (1) reward function (1) reward learning (1) diffusion model (1) salient object detection (1) cross-modal alignment (1) generative adversarial network (1) adversarial imitation learning (1) inference efficiency (1) retrieval-augmented generation (1) large vision-language model (1) visual token (1) inference latency (1)