About me
I am a third-year PhD student in CS at the University of Wisconsin-Madison, advised by Professor Frederic Sala and a member of the Sprocket Lab.
My research takes a data-centric approach to large language models. I am particularly interested in:
- improving their capabilities through data selection, curation, and automated agentic data synthesis
- evaluating them faithfully through verifiable outcomes and by decomposing complex tasks into distinct skills
Before that, I earned my B.S., also at the University of Wisconsin-Madison, with a double major in Computer Science & Mathematics.
I am actively seeking internship opportunities in related fields. Please feel free to reach out to me at zhiqi [at] cs [dot] wisc [dot] edu, or take a look at my resume.
News
- July 2026 Two papers accepted to COLM 2026!
- May 2026 Fine-Tuning Small Reasoning Models for Quantum Field Theory accepted to PAI26.
Publications
Conferences & Journals
Models Can Model, But Can’t Bind: Structured Grounding in Text-to-Optimization
Zhiqi Gao*, Albert Ge*, Alexander Michael Berenbeim, Nathaniel D. Bastian, Frederic Sala
COLM (Conference on Language Modeling) 2026
Preliminary version (as “OR-LLM-Bench”) at ICLR 2026 DATA-FM Workshop
arXiv Code DatasetTest-Time Scaling Makes Overtraining Compute-Optimal
Nicholas Roberts, Sungjun Cho, Zhiqi Gao, Tzu-Heng Huang, Albert Wu, Gabriel Orlanski, Avi Trost, Kelly Buchanan, Aws Albarghouthi, Frederic Sala
COLM (Conference on Language Modeling) 2026
arXivFine-Tuning Small Reasoning Models for Quantum Field Theory
Nathaniel S. Woodward, Zhiqi Gao, Yurii Kvasiuk, Kendrick M. Smith, Frederic Sala, Moritz Münchmeyer
2026 Conference on Physics and AI (PAI26)
Under review at MLST (Machine Learning: Science and Technology)
arXiv Code DatasetPretrained Hybrids with MAD Skills
Nicholas Roberts, Samuel Guo, Zhiqi Gao, Satya Sai Srinath Namburi GNVV, Sonia Cromp, Chengjun Wu, Chengyu Duan, Frederic Sala.
COLM (Conference on Language Modeling) 2025
arXivTheoretical Physics Benchmark (TPBench) – a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics
Daniel J.H. Chung, Zhiqi Gao, Yurii Kvasiuk, Tianyi Li, Moritz Münchmeyer, Maja Rudolph, Frederic Sala, Sai Chaitanya Tadepalli.
MLST (Machine Learning: Science and Technology) 2025
MMLS (Midwest Machine Learning Symposium) 2025 Lightning Talk
arXiv Website Dataset
Workshop Publications
Test-time Scaling Techniques in Theoretical Physics—A Comparison of Methods on the TPBench Dataset
Zhiqi Gao*, Tianyi Li*, Yurii Kvasiuk, Sai Chaitanya Tadepalli, Maja Rudolph, Daniel J.H. Chung, Frederic Sala, Moritz Münchmeyer
NeurIPS 2025 Machine Learning and the Physical Sciences (ML4PS) Workshop
arXivRe-Structuring CLIP’s Language Capabilities
Zhiqi Gao, Frederic Sala.
MMLS (Midwest Machine Learning Symposium) 2025
Poster PDF Blog Post
Industry Experience
Roblox Corporation
- Designed, developed, and deployed a full-stack project with a Slack Bot that integrates Vector Database & Large Language Models (LLMs) which can perform complex Q&A based on custom knowledge by Retrieval-Augmented Generation (RAG), resulting in a better solution that outperformed the existing Question Answering Slack Bot within the company.
- Created an efficient data pipeline, ingesting diverse documents (Confluence, Stack Overflow, GitHub) and generating vector embeddings for rapid retrieval.
Teaching Experience
Comp Sci 540 — Introduction to Artificial Intelligence
Comp Sci 300 — Programming II
Service
Reviewer: NeurIPS 2024, 2025, 2026 · COLM 2026 · TMLR 2026
Undergraduate Projects
Tessellations on the Poincaré Half-Plane and Disk
Advisor: Professor Andrew Zimmer.
- Contributed to the “Tessellations on the Poincaré Half-Plane and Disk” project in the Summer 2022 UW-Madison Research Experiences for Undergraduates (REU) in Analysis funded by the National Science Foundation (NSF). Developed a visualization tool to demonstrate principles of hyperbolic geometry for education purposes, allowing users to generate and explore tessellations on the Poincaré disk and half-plane, aiding students in comprehending complex concepts.
Poster PDF
Random Walks on Groups
Advisor: Dr. Nate Fisher
- Participated in a group project at Madison Experimental Mathematics Lab. Implemented Mathematica simulations to investigate the asymptotic properties of random walks on algebraic structures like $\mathbb{Z}^n$ and the Heisenberg group, quantifying metrics and analyzing their long-term pattern, such as expected travel distance, expectation of hitting time, and distribution of hitting location.
Poster PDF
Miscellaneous
Outside of research, I have spent many years studying classical Chinese literature and cultural history.
I have memorized around 500 works of classical Chinese poetry, ci lyric poetry, and prose, and have written over 70 original pieces in traditional forms, including poems, ci, prose, and couplets.
Before moving abroad, I served as a volunteer docent at Zhihua Temple (智化寺) in Beijing, and I am comfortable giving informal guided tours of Beijing’s historical sites, such as the Summer Palace and the Forbidden City.