Miaosen Zhang

knowledge distillation (3) reinforcement learning (2) transfer learning (2) model compression (2) vision transformer (1) image retrieval (1) preference learning (1) information retrieval (1) multimodal learning (1) model architecture (1) multi-modal learning (1) model decomposition (1) language model (1) scaling law (1) vision-language model (1) model fine-tuning (1) data quality (1) preference-based reinforcement learning (1) vision model (1) multimodal reasoning (1)