Shu Yang

large language model (8) inference acceleration (3) causal inference (3) model compression (3) mechanistic interpretability (2) knowledge distillation (2) spiking neural network (2) semiparametric efficiency (2) benchmark evaluation (1) text classification (1) zero-shot learning (1) model misspecification (1) feature extraction (1) question answering (1) transfer learning (1) post-training quantization (1) bias detection (1) information retrieval (1) policy learning (1) off-policy evaluation (1)