Shengjie Sun

large language model (2) model compression (2) preference learning (1) knowledge distillation (1) model pruning (1) bayesian optimization (1) reward learning (1) human feedback (1) vision-language model (1) preference-based reinforcement learning (1) vision-language preference learning (1) embodied manipulation (1) language-conditioned preference (1) layer sparsity (1) activation correlation (1) reinforcement learning (1)