Bo Tang

large language model (7) offline reinforcement learning (3) retrieval-augmented generation (3) reinforcement learning (2) adversarial attack (2) text generation (2) budget constraint (2) instruction following (2) conditional variational autoencoder (2) benchmark evaluation (2) chain-of-thought reasoning (1) information extraction (1) data augmentation (1) dialogue generation (1) off-policy evaluation (1) natural language inference (1) policy learning (1) preference learning (1) policy evaluation (1) face recognition (1)