arXiv subjects

Sophie Li

Publications and source records attributed to Sophie Li.

5 recordsLinked to original sources

arXiv2026

A Unified Subject Map for 130 Years of Physics

More than a century of physics is recorded in the American Physical Society (APS) archive, but the corpus cannot be analyzed as a single, time-resolved object because its subject metadata are fragmented across eras with no shared vocabulary. We close this gap by using a frontier large language model to retrospectively assign the modern Physics Subject Headings (PhySH) to the historical archive, yielding a unified subject map for every APS paper from 1893 to 2025. The resulting map not only reproduces century-scale disciplinary arcs but also resolves the fine-grained lifecycles of individual ideas, materials, techniques, and discoveries across a vocabulary of over 3,000 PhySH Concepts. The map turns a fragmented archive into a quantitative substrate for systematic search and for data-driven studies of how physics evolves.

physics.hist-ph↗

arXiv2025

Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

Large language models (LLMs) improve reasoning accuracy when generating multiple candidate solutions at test time, but standard methods like Best-of-N (BoN) incur high computational cost by fully generating all branches. Self-Truncation Best-of-N (ST-BoN) mitigates this by truncating unpromising paths early, but its reliance on consistency-based heuristics is a limitation as it does not directly evaluate branch quality. We present KL-Adjusted Pruned Path Algorithm (KAPPA), an inference-time method that combines Kullback-Leibler divergence, confidence, and entropy into a principled scoring function to guide progressive pruning. By promoting diversity during exploration and selectively eliminating low-scoring branches, KAPPA maintains accuracy while substantially reducing memory and token usage. Experiments on GSM8K and MATH500 with DeepSeek-R1-Distill-Qwen-1.5B and Qwen2.5-7B-Instruct demonstrate that KAPPA stabilizes performance in smaller models and achieves up to ~60% reduction in peak memory and ~90% reduction in total token generation relative to BoN, with minimal impact on accuracy.

cs.LG↗

arXiv2025

Necklaces, permutations, and periodic critical orbits for quadratic polynomials

Let $G_n$ denote the $n^{\rm th}$ Gleason polynomial, whose roots correspond to parameters $c$ such that the critical point $0$ is periodic of exact period $n$ under iteration of $z^2 + c$, and let $\bar{G}_n$ denote the reduction of $G_n$ modulo $2$. Buff, Floyd, Koch, and Parry made the surprising observation that the number of real roots of $G_n$ is equal to the number of irreducible factors of $\bar{G}_n$ for all $n$. We provide a bijective proof for this result by first providing explicit bijections between (a) the set of real roots of $G_n$ and the set $\bar{N}(n)$ of equivalence classes of primitive binary necklaces of length $n$ under the inversion map swapping $0$ and $1$; and (b) the set of irreducible factors of $G_n$ modulo 2 and the set $\tilde{N}^+(n)$ of binary necklaces which are either primitive of length $n$ with an even number of $1$'s or primitive of length $n/2$ with an odd number of $1$'s. We then provide an explicit bijection, closely related to Milnor and Thurston's kneading theory, between $\bar{N}(n)$ and $\tilde{N}^+(n)$. In addition, we provide explicit bijections between $\bar{N}(n)$, the set ${\rm CUP}(n)$ of cyclic unimodal permutations of $\{ 1,\ldots,n \}$, and the set $N^-(n)$ of primitive binary necklaces of length $n$ with an odd number of $1$'s.

math.CO↗

arXiv2024

Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges

Speech is a fundamental aspect of human life, crucial not only for communication but also for cognitive, social, and academic development. Children with speech disorders (SD) face significant challenges that, if unaddressed, can result in lasting negative impacts. Traditionally, speech and language assessments (SLA) have been conducted by skilled speech-language pathologists (SLPs), but there is a growing need for efficient and scalable SLA methods powered by artificial intelligence. This position paper presents a survey of existing techniques suitable for automating SLA pipelines, with an emphasis on adapting automatic speech recognition (ASR) models for children's speech, an overview of current SLAs and their automated counterparts to demonstrate the feasibility of AI-enhanced SLA pipelines, and a discussion of practical considerations, including accessibility and privacy concerns, associated with the deployment of AI-powered SLAs.

eess.AS↗

arXiv2024

A System for Critical Facility and Resource Optimization in Disaster Management and Planning

Disruptions to medical infrastructure during disasters pose significant risks to critically ill patients with advanced chronic kidney disease or end-stage renal disease. To enhance patient access to dialysis treatment under such conditions, it is crucial to assess the vulnerabilities of critical care facilities to hazardous events. This study proposes optimization models for patient reallocation and the strategic placement of temporary medical facilities to bolster the resilience of the critical care system, with a focus on equitable outcomes. Utilizing human mobility data from Texas, we evaluate patient access to critical care and dialysis centers under simulated hazard scenarios. The proposed bio-inspired optimization model, based on the Ant Colony optimization method, efficiently reallocates patients to mitigate disrupted access to dialysis facilities. The model outputs offer valuable insights into patient and hospital preparedness for disasters. Overall, the study presents a data-driven, analytics-based decision support tool designed to proactively mitigate potential disruptions in access to critical care facilities during disasters, tailored to the needs of health officials, emergency managers, and hospital system administrators in both the private and public sectors.

cs.NE↗