Zhiming Li

deep reinforcement learning (2) program synthesis (2) shortcut learning (1) few-shot learning (1) self-attention mechanism (1) domain generalization (1) relation extraction (1) bias mitigation (1) policy learning (1) prototype learning (1) model aggregation (1) out-of-distribution generalization (1) statistical machine translation (1) data heterogeneity (1) adversarial robustness (1) global model (1) abstract syntax tree (1) interpretable policy (1) decision rationale alignment (1) federated learning (1)