Computer Science student and research assistant at the University of Minnesota, interested in efficient LLM training and inference systems.

Website · CV · Email · LinkedIn

1. Integrated Training & Inference — 训推一体化
2. Algorithm–System Co-Design — 算法与系统协同设计
3. LLM Post-Training — 大语言模型后训练
4. On-Device AI — 端侧人工智能

• InferZO: Inference-Native Zeroth-Order Optimization for LLMs — under review at ICLR 2027; arXiv preprint. Inference-native execution for LLM training and inference co-serving (code)
• EasyLocomo — reproducible evaluation for long-horizon LLM memory systems
• Auto-Chronicle Gaokao — a state-machine narrative engine with multi-agent simulation

University of Minnesota, Twin Cities
Bachelor’s in Computer Science · 2025–2027 · GPA: 4.0/4.0

Beijing University of Posts and Telecommunications
Artificial Intelligence · 2023–2025 · GPA: 3.85/4.0 · Rank: 1/180