Zhihong Deng

attention mechanism (2) few-shot learning (2) zero-shot learning (1) knowledge distillation (1) sequential decision-making (1) variational inference (1) epistemic uncertainty (1) protein structure prediction (1) cross-entropy loss (1) transfer learning (1) machine translation (1) language modeling (1) text representation (1) markov chain monte carlo (1) vision transformer (1) parameter-efficient fine-tuning (1) sequence model (1) bayesian neural network (1) representation learning (1) causal inference (1)