Wenhan Xia

regret bound (2) online learning (2) large language model (2) feature distribution (1) knowledge distillation (1) data augmentation (1) in-context learning (1) text generation (1) synthetic data generation (1) output distribution (1) regret guarantee (1) model-free reinforcement learning (1) adversarial environment (1) online adaptation (1) trajectory planning (1) obstacle avoidance (1) analogical reasoning (1) reasoning task (1) text augmentation (1) bidirectional alignment (1)