Qinyuan Cheng

large language model (10) vision-language model (3) reinforcement learning (2) contrastive learning (2) dialogue system (2) text generation (2) style transfer (1) model evaluation (1) hyperparameter optimization (1) chain-of-thought reasoning (1) temporal reasoning (1) dialogue generation (1) multi-task learning (1) information retrieval (1) code generation (1) preference learning (1) multimodal learning (1) policy learning (1) visual reasoning (1) preference optimization (1)