Skip to content

Category

small language model

2,906 papers

#small language model Open access Sep 2026

The Wind on a Sail and the Apparent Place of a Star Are One and the Same Formula ── the formula that turns a boat-to-wind ratio into an apparent wind gives an aberration of 20.492653 arcseconds when fed the Earth's beta=9.935118x10^-5 ── the two formulas part at beta=0.5, where they differ by 3.4349 degrees ── [Paper 524]

The apparent wind of a sailing craft and the aberration of starlight are taught as separate matters. What this paper shows is that at low speed they are one and the same function, and that they part only where the rule for composing velocities changes. No new theorem or law is claimed. Scope of this paper (scope note):...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

vcfclick: embedded VCF databases with auditable natural-language queries

Small VCF databases, one per cohort. Variants, genotypes, and samples live in either chDB (embedded ClickHouse) or DuckDB; gene and ClinVar annotations live in a sibling DuckDB file. A bundled Model Context Protocol server exposes a small set of tools so a language-model client can query the cohort in natural language...

Paulo A. F. Nuin · 0 citations
#small language model Open access Sep 2026

理容所と美容所 ── 1店あたり2人、そして高齢化した県ほど理容所が多い

理容所・美容所の数を、衛生行政報告例(令和6年度末、厚生労働省)と経済センサス(令和3年、産業小分類782・783)で数え、都道府県ごとに比べた。 数は合わない。理容所は107,995対86,476(+24.9%)、美容所は277,752対161,280(+72.2%)。衛生行政報告例は許可を受けた施設、経済センサスは事業所である。 1店あたりの従業者は2人前後。理容所は1.80...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

Electric Vehicle Sales and Market Trend Analysis Using Python Power BI

Sales records for electric vehicles (EVs) are often examined in spreadsheets, or in forecasting studies that say little about how the data were prepared and queried. This paper documents a small, reproducible analytics workflow for EV sales and applies it to a demonstration dataset of 440 records covering ten Indian st...

LAVUDI NAVEEN · 0 citations
#small language model Open access Sep 2026

Selberg Integrals and Particle–Hole Duality in the Richardson–Gaudin Pairing Model

Authorship, provenance, and verification. The scientific problem, original method, and research direction belong to W. V. Pogosov. This project builds on his published and unpublished work developed before the involvement of an advanced large language model (LLM). During the subsequent LLM-assisted phase, the LLM produ...

W. V. Pogosov · 0 citations
#small language model Open access Sep 2026

Attractor-Basin Failure under Transient Perturbations and the Limits of Spectral Trajectory Summaries

We study how large transient inputs cause post-perturbation memory failure in small recurrent neural networks (RNNs), and whether spectral summaries of early hidden-state trajectories provide information beyond simpler time-domain descriptions. Mechanistically, each of three tanh memory RNNs contained two stable zero-i...

Sohan Poudel · 0 citations
#small language model Open access Sep 2026

Initialization DNA: Sparse Weight-Space Programs for Accelerating Small Transformer Language Model Training

This record contains the preprint manuscript (submitted to Pattern Recognition, PR-D-26-12736 Revision R1) along with the complete replication package, frozen DNA specifications, execution scripts, and 400 training run logs.This archive contains the complete replication package, frozen DNA specifications, core executio...

Terrence Yang · 0 citations
#small language model Open access Sep 2026

The Strategic Role of Human Resource Management in Facilitating Artificial Intelligence Adoption: A Multi-Industry Perspective

Artificial Intelligence (AI) has emerged as one of the most transformative technologies of the twenty-first century, fundamentally reshaping organizational processes, business models, and workforce dynamics across industries. The rapid advancement of machine learning, generative AI, natural language processing, robotic...

Niroopa A, Srikanth I. G., G. Srinivasa et al. · 0 citations
#small language model Open access Sep 2026

Supplemental Material for: Oxygenation During Sequential Drinking in Healthy Adults and Adults with Severe or Very Severe Chronic Obstructive Pulmonary Disease

Introduction: Sequential drinking requires repeated swallowing with brief interruptions in breathing. Speech-language pathologists may notice oxygen saturation changes during drinking tasks, but interpretation is difficult without healthy comparison data collected at the time of physiologically verified swallowing acti...

figshare admin karger, Salim Alani, Julie A.G. et al. · 0 citations
#small language model Open access Sep 2026

T19. DECOMPOSING PHENOTYPIC DISPERSION IN 16P11.2 COPY NUMBER VARIATION ACROSS TRAITS AND INDIVIDUALS

Background Rare recurrent copy number variants (CNVs) are associated with risk for developmental and neuropsychiatric disorders but demonstrate considerable clinical heterogeneity at the individual level. It remains unclear how between-person variability within CNV groups compares to the general population, differs acr...

Tyler Dietterich, Rune Bøen, Hoki Fung et al. · 0 citations
#small language model Open access Sep 2026

ENGRAFT: ENgram GRadient Routing-Aware Fact Transplant

Second public release. v0.1.0 wrote eight facts, one trigger each. This one writes a small world: one hundred facts about an invented character (Quail), learned from sentences that use them, and recalled by the real llama.cpp engine on sentences it never saw. What changed since v0.1.0 Usage-corpus descent. The variable...

fulvian · 0 citations
#small language model Open access Sep 2026

Initialization DNA: Sparse Weight-Space Programs for Accelerating Small Transformer Language Model Training

This record contains the preprint manuscript (submitted to Pattern Recognition, PR-D-26-12736 Revision R1) along with the complete replication package, frozen DNA specifications, execution scripts, and 400 training run logs.This archive contains the complete replication package, frozen DNA specifications, core executio...

Terrence Yang · 0 citations

From tech blogs

See all →
Microsoft Research Blog Oct 12, 2026

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.