Skip to content
View GaokaiZhang's full-sized avatar

Block or report GaokaiZhang

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
GaokaiZhang/README.md

👋 Hi there, I'm Gaokai Zhang

  • 🎓 M.S. student in Intelligent Information Systems (MIIS) at CMU LTI (2025-2027)
  • 💡 Dual B.S. from UIUC & ZJU in Computer and Electronics Engineering
  • 🧠 Passionate about LLMs, long-context reasoning, and reinforcement learning
  • 🛠️ Previously interned at Microsoft Research Asia (MSRA) — worked on LongRoPE2 (ICML'25) and LoongRL (ICLR'26 Oral) for long-context LLM reasoning
  • 🔬 Currently working on SWE-Bench code-generation agents with Prof. Lei Li's lab at CMU
  • 📫 Reach me: gaokaiz2@andrew.cmu.edu

🔬 Recent Research

  • 🧾 LongRoPE2 — Extended LLM context to 128K tokens with >98.5% short-context retention (ICML 2025)
  • 🚀 LoongRL — RL framework enabling 7B models to outperform 32B LRMs on 100k-200k token reasoning (ICLR 2026 Oral)
  • 🐒 Stochastic Monkeys — Robustness benchmarking of LLM safety alignment

⚙️ Tech I Work With

Python PyTorch Hugging Face vLLM DeepSpeed Megatron-LM Slurm


💬 Let's Connect

LinkedIn Google Scholar Email Personal Site

Pinned Loading

  1. Network-Parallelism Network-Parallelism Public

    Python 2 1

  2. lm-evaluation-harness lm-evaluation-harness Public

    Forked from EleutherAI/lm-evaluation-harness

    A framework for few-shot evaluation of language models.

    Python 1

  3. verl-project/verl verl-project/verl Public

    verl: Volcano Engine Reinforcement Learning for LLMs

    Python 19.9k 3.4k