Austin Xu

metric learning (3) large language model (3) reinforcement learning (2) mahalanobis distance (2) group relative policy optimization (2) direct preference optimization (1) preference learning (1) semantic segmentation (1) language model evaluation (1) retrieval-augmented generation (1) depth estimation (1) language modeling (1) low-rank matrix (1) human feedback (1) supervised fine-tuning (1) model evaluation (1) generative adversarial network (1) recommendation system (1) pairwise comparison (1) data augmentation (1)