Ning Yang

zero-shot learning (1) semi-supervised learning (1) robotic manipulation (1) information bottleneck (1) visual question answering (1) self-supervised learning (1) weakly supervised learning (1) chain-of-thought reasoning (1) code generation (1) temporal information (1) adversarial training (1) deep learning (1) inverse reinforcement learning (1) policy iteration (1) multimodal retrieval (1) safe reinforcement learning (1) vision-language model (1) bi-level optimization (1) multimodal large language model (1) contrastive learning (1)