Route-Consistent Adaptation for Stable Quantization of Mixture-of-Experts Models with Theoretical Guarantees
NeurIPS, 2026
I am Longteng Zhang, a final-year PhD candidate in the Thrust of Data Science and Analytics at HKUST(GZ), advised by Xiaowen Chu and Luo Qiong. My research interest lies broadly in optimization and AI topics.
My recent research focuses on building efficient systems capable of reasoning and optimization in long-horizon and complex environments.
I'm always open to discussing research ideas, collaborations, and research or career opportunities. Feel free to reach out via:
NeurIPS, 2026
AAAI, 2026
ICDCS, 2023
IJCAI, 2023
Preprint
Preprint
Sep 2023 – Present
Ph.D. Candidate · Data Science and Analytics
Supervisors: Prof. Xiaowen Chu and Prof. Qiong Luo
Sep 2017 – Jun 2021
B.S. · Computer Science and Technology
Advisor: Prof. Hongliang Li
May 2026 – Present
Research Intern · Project Up Program
Efficient post-training for long-horizon agents.
Sep 2022 – Sep 2023
Research Assistant
Efficient LLM training and fine-tuning, runtime benchmarking, and performance analysis of NVIDIA's Hopper architecture.
Sep 2022 – Sep 2023
Research Assistant · Department of Computer Science
Efficient training and optimization of deep learning models.
May 2021 – Oct 2021
Researcher
Mobile AI training and inference for Exynos 2200.