Jinyi Liu

large language model (2) reinforcement learning (2) policy optimization (1) temporal reasoning (1) question answering (1) multimodal learning (1) robot learning (1) optimism in face of uncertainty (1) elo rating (1) continuous control (1) policy improvement (1) vision language model (1) multimodal large language model (1) exploration strategy (1) optimism-based exploration (1) signal processing (1) drug discovery (1) retrieval-augmented generation (1) multi-agent debate (1) uncertainty quantification (1)