Hi, I'm Jingwen Fan (范敬文) 👋

AI/ML learner focusing on Large Language Models (LLMs).
Passionate about the full LLM lifecycle from pre-training & fine-tuning to alignment (RLHF) and inference optimization.

---

🚀 Current Focus

• LLM Alignment: RLHF, PPO, DPO & Retrieval-Augmented Generation (RAG)
• Learning: Agentic Workflows, DeepSpeed & model quantization (AWQ / GPTQ)

🎓 Background

• Education: Qilu University of Technology (QLUT)
• Research Interests: Reward modeling, context window extension, chain-of-thought (CoT)

🎯 Goals

• Seeking 2026 Summer Internship opportunities
  (LLM / Multimodal / Agent / RLHF)

📟 最新文章

• 大模型如何降低幻觉：从不可消除，到可工程化控制
• DreamGym：用经验合成而非真实交互，扩展大模型 Agent 的学习能力
• 我发现：大模型检索里，最划算的 Query Rewrite 不是“重写语义”，而是“只翻译”
• 模型自进化：个人记录

💌 联系方式

• Email: 867762462f@gmail.com
• Zhihu: 二次函数