4 papers
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…
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…
Large Blue Spectral Index From a Conformal Limit of a Rotating Complex Scalar
Daniel J. H. Chung, Sai Chaitanya Tadepalli
One well known method of generating a large blue spectral index for axionic isocurvature perturbations is through a flat direction not having a quartic potential term for the radia…
Power Spectrum in the Chaotic Regime of Axionic Blue Isocurvature Perturbations
Daniel J. H. Chung, Sai Chaitanya Tadepalli
Large blue tilted spectral index axionic isocurvature perturbations can be produced when the axion sector is far out of equilibrium during inflation through an initial Peccei-Quinn…