Qingru Zhang

model compression (3) language model (2) knowledge distillation (2) neural network pruning (2) language model alignment (1) preference learning (1) uncertainty quantification (1) language modeling (1) reward modeling (1) preference optimization (1) model pruning (1) computational efficiency (1) reinforcement learning from human feedback (1) low-rank approximation (1) sparse approximation (1) outlier detection (1) attention mechanism (1) lipschitz continuity (1) robust learning (1) multi-agent reinforcement learning (1)