I am an M.S. student in Information Management at the University of Illinois Urbana-Champaign (UIUC).

I work on ML systems for large-scale models: inference engines and expert streaming for MoE models, distributed training and rollout infrastructure, RL post-training systems, and GPU compiler and kernel-level correctness. I like to sit between the machine and the model — how weights are read from storage, how collectives and thread teams are sized, and whether a resource plan and the runtime agree about what will actually be built. I keep a research background in LLM reasoning, multimodal learning, and agent safety, and I bring an upstream-first habit to all of it: reproduce failures in real production stacks, then contribute fixes with regression tests and measured before/after numbers.

My research experience includes research at UIUC on efficient ML systems, the Tencent Youtu AI Lab on content-safety and multimodal research, the SUFE FinAI Center (advised by Prof. Liwen Zhang) on financial reasoning and agent safety, Shanghai Jiao Tong University (advised by Prof. Xiaodong Gu) on LLM for Code, and the Head Office of ICBC (Private Banking Department) on scientist-discovery agents.

🎓 I plan to apply to Ph.D. programs in ML systems for Fall 2028. I am happy to hear from faculty and students working on efficient inference, training infrastructure, or GPU kernels.

Research Interests

• ML Systems for Large Models — inference engines and expert streaming for MoE models, KV-cache and memory budgeting, attention and quantization kernels, performance profiling
• Distributed Training & Rollout — ZeRO-3, FSDP, Megatron-LM, Hybrid Engine, collective synchronization and deadlock debugging, RL rollout systems (verl, TRL)
• GPU Compiler & Kernel Correctness — MLIR passes, Triton/CUDA kernel-level debugging, reproducible regression tests

Selected Publications

• 📝 GPTQ under random rotation — How Much Does Random Rotation Help GPTQ? Sharp Worst-Case Rate Gaps in the High-Rate Regime — single author, under review. arXiv:2611.01669 · PDF
• 📝 Recency Is the Wrong Axis — Recency Is the Wrong Axis: A Negative Result on Windowed Deepest-Plane KV Caching in Looped Language Models — arXiv preprint, co-author. arXiv:2610.34436
• 📝 ScaleRLT — ScaleRLT: Exact Log-Probabilities and Fast Deferred Rollouts for Reinforcement Learning on Looped Transformers — arXiv preprint, co-author. arXiv:2610.34427
• 📝 Certified Sparse Attention — Certified Sparse Attention via Perturbed Retrieval — arXiv preprint, single author. arXiv:2610.24991
• 📝 BreadthKV — Spend Bytes on Breadth: Precision–Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning — arXiv preprint, single author. arXiv:2610.05685
• 📝 FinVault — Benchmarking Financial Agent Safety in Execution-Grounded Environments — arXiv preprint, co-first author. arXiv:2601.07853

All publications

Open-Source Contributions (ML Systems)

26 public merged pull requests across 16 public upstream projects. Top five projects by GitHub stars: Kubernetes, vLLM, colibri, DeepSpeed, and LLVM. View all contribution links.

Get in Touch

• ✉️ Email: runguol2@illinois.edu
• 💬 WeChat: RunguoLi2004
• 🐙 GitHub: github.com/LiRunGuo
• 🎓 Google Scholar: Runguo Li
• 🆔 ORCID: 0009-0002-0832-6227
• 📄 Curriculum Vitae