Kechen Jiao

model compression (1) reinforcement learning (1) sample efficiency (1) benchmark evaluation (1) chain-of-thought reasoning (1) preference optimization (1) vision language model (1) embodied agent (1) uncertainty estimation (1) dynamics model (1) inference efficiency (1) retrieval-augmented generation (1) model degradation (1) cross entropy (1) synthetic sample (1) chain of thought (1) numerical method (1) multi-agent system (1) model-based offline reinforcement learning (1) conversational retrieval (1)