activity
20242026
collaborators

6 papers

cs.LG2026

Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization

Zhiqi Gao, Albert Ge, Alexander Berenbeim +2

Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter…

cs.LG2026

Fine-Tuning Small Reasoning Models for Quantum Field Theory

Nathaniel S. Woodward, Zhiqi Gao, Yurii Kvasiuk +3

Despite the growing application of Large Language Models (LLMs) to theoretical physics, there is little academic exploration into how domain-specific physics reasoning ability deve…

cs.LG2026

Test-Time Scaling Makes Overtraining Compute-Optimal

Nicholas Roberts, Sungjun Cho, Zhiqi Gao +7

Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling…

cs.LG2025

Test-time Scaling Techniques in Theoretical Physics -- A Comparison of Methods on the TPBench Dataset

Zhiqi Gao, Tianyi Li, Yurii Kvasiuk +5

Large language models (LLMs) have shown strong capabilities in complex reasoning, and test-time scaling techniques can enhance their performance with comparably low cost. Many of t…

cs.LG2025

Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics

Daniel J. H. Chung, Zhiqi Gao, Yurii Kvasiuk +5

We introduce a benchmark to evaluate the capability of AI to solve problems in theoretical physics, focusing on high-energy theory and cosmology. The first iteration of our benchma…

cs.LG2024

Pretrained Hybrids with MAD Skills

Nicholas Roberts, Samuel Guo, Zhiqi Gao +5

While Transformers underpin modern large language models (LMs), there is a growing list of alternative architectures with new capabilities, promises, and tradeoffs. This makes choo…