Haoxiang Wang

reinforcement learning from human feedback (3) reward modeling (2) intermediate domain (2) gradual domain adaptation (2) few-shot learning (2) preference modeling (2) long short-term memory (2) speech emotion recognition (2) data augmentation (1) optimal transport (1) 3d reconstruction (1) preference alignment (1) convex optimization (1) convergence analysis (1) domain adaptation (1) multi-task learning (1) neural rendering (1) unsupervised domain adaptation (1) implicit representation (1) transfer learning (1)