Zhenhua Huang

model compression (1) deep reinforcement learning (1) reinforcement learning (1) transfer learning (1) curriculum learning (1) knowledge distillation (1) policy learning (1) semantic alignment (1) noise robustness (1) consistency regularization (1) vision-language model (1) student model (1) deep q-network (1) dialogue system (1) dialogue policy (1) dynamic reward (1) dialogue agent (1) user simulator (1) noisy environment (1) intra-class knowledge (1)