Yixin Zhou

large language models, instruction tuning, reinforcement learning, RLHF, RLAIF, test-time RL, reasoning, chain-of-thought, self-play, search-augmented models

2022 – Present

transformers, multimodal models, vision-language models, embeddings, retrieval-augmented generation, perception encoders, video understanding, speech models

2022 – Present

model deployment, inference optimization, distributed training, serving systems, model compression, quantization, context engineering, agent frameworks, workflow orchestration

2022 – Present

Suggest Expertise