Skip to content

Category

small language model

2,968 papers

#small language model Book Open access Sep 2026

Large-Model-Enabled UAV Inspection for Transmission Lines: A Vision-Language Reasoning and Lightweight Detection Framework

Unmanned Aerial Vehicle (UAV) inspection has become an important technical approach for improving the safety, efficiency, and traceability of transmission-line operation and maintenance. However, automatic interpretation of UAV images remains difficult because transmission-line defects are often small, partially occlud...

Jun Dong, Jundong Huang, Kunpeng Liu et al. · 0 citations
#small language model Open access Sep 2026

Measurement Invariance and Validity of Mathematics Self-Concept Scale in TIMSS 2023: Evidence from Hong Kong

The present study examined the factor structure, measurement invariance across sex and language, concurrent and discriminant validity and achievement-related criterion validity of the eight-item mathematics self-concept scale from TIMSS 2023 in a sample of 4463 eighth-grade students in Hong Kong. Cronbach’s alpha was h...

Onur Ramazan · 0 citations
#small language model Open access Sep 2026

Do Large Language Models Correct False Technical Premises? An Empirical Case Study in Computer Science Question Answering

Large language models (LLMs) are increasingly used for coding assistance, education, and technical question answering. A particular reliability problem arises when a question contains a false technical premise: instead of correcting the assumption, a model may accept it and construct a plausible answer around it. This...

Nabeel Haider Rizvi · 0 citations
#small language model Open access Sep 2026

Kelvin's Calculation Was Never Refuted; What Was Replaced Was the Reservoir ── From one and the same solar luminosity, gravitational contraction gives 9.4248x10^6 years and fusion 1.0358x10^10 ── against the Earth's radiometric age of 4.54x10^9 years the first is 481.71 times too short and the second 2.28 times too long ── the two mechanisms differ by 1099.05, and the division itself is correct in both ── [Paper 497]

Kelvin’s age of the Sun is taken to have failed because the calculation was wrong. This paper shows that both divisions are correct and only the estimate of the reservoir differs──one luminosity yielding two ages a factor of 1099.05 apart. No new theorem or law is claimed. Scope of this paper (scope note): No new theor...

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

A correlative approach to the integration of diagnostic features of gas piston electric units

RELEVANCE. Gas-piston electric units with synchronous generators with excitation from permanent magnets are widely used in the oil industry and in small distributed power engineering. Continuous technical diagnostics are an effective means of increasing their operational readiness and reliability. The article examines...

A. Zayniev, M. Khakimyanov · 0 citations
#small language model Open access Sep 2026

Comparative Analysis of Requirements Specification Methods for Game Software

Based on a comparative analysis of five methods across the criteria of formality degree, applicability to non-functional requirements, compatibility with agile methodologies, and learning threshold, it is established that no single method is universal.

M. Elchaninov · 0 citations
#small language model Open access Sep 2026

Siesta: Identitas yang Koheren pada Model Bahasa Orchestrator dengan Kepribadian Emergen

Siesta is an independent research project exploring identity coherence in a small-scale Indonesian-language orchestrator model — a "brain" that stays behaviorally consistent while delegating specialized tasks to separate hidden models. Built entirely from scratch (not fine-tuned) on limited consumer hardware (GPU/TPU w...

Evan Almunawar · 0 citations
#small language model Open access Sep 2026

Improving individual cattle identification for livestock management systems using vision transformer embeddings and FAISS

The growing demand for cattle products has created an urgent need for large-scale farms equipped with automated management systems to ensure sustainable and efficient livestock farming practices. One critical challenge is the accurate identification of individual cattle, as errors in identification can negatively aff...

Shiekhah al-Binali, Abrar Al-Amoudi, Abdulrahman Javaid · 0 citations
#small language model Open access Sep 2026

Topological Cross-Domain Transfer in Autonomous Systems: Structural Isomorphism Training

Structural isomorphism training for cross-domain transfer in small language models, validated via the gnarp model lineage and Self-Falsifying Orchestrator. One of 135 dated defensive publications in the CatQualia record. Collection DOI: https://doi.org/10.5281/zenodo.22751107 Original publication: https://catqualia.com...

Christopher Betances · 0 citations
#small language model Open access Sep 2026

Diagnostic performance of a specific local Turkish large language model in detecting alcohol use disorder across internal medicine practice: A 42-patient pilot study

Objective: Alcohol use disorder (AUD) is underdiagnosed in internal medicine. We evaluated a local large language model (LLM), fine-tuned on a Turkish medical corpus, for detecting AUD across outpatient, emergency and inpatient settings. Method: We retrospectively analyzed 42 adult patients at a tertiary state hospital...

İlker Boğa, Mete Üçdal · 0 citations
#small language model Review Open access Sep 2026

Agentic AI for Digital Product Passport Documentation: A Feasibility Study on Heterogeneous Manufacturing Documents

Observations suggest that the retrieval infrastructure adapted to manufacturer vocabulary and complementary deterministic tools may be more consequential design priorities for DPP deployments supported by agentic AI than further work on orchestration complexity.

Lukas Wohlschläger, Arne Falkenreck, J. Fottner · 0 citations
#small language model Open access Sep 2026

A Lagrange Multiplier Is a Temperature Here and a Pressure Next Door ── The multiplier beta from maximising entropy agrees with an independently computed dS/dE at 0.700000000 against 0.700000000, and again at 1.900000000 for beta=1.9 ── it does not agree with a wrong value of 0.9 ── the same device appears in Paper 196 as the multiplier enforcing incompressibility, where it is the pressure: what the multiplier is, the constraint decides ── [Paper 494]

A Lagrange multiplier is taken to be an auxiliary quantity that appears mid-calculation. This paper shows that the multiplier agrees digit for digit with an independently defined physical quantity──and that which quantity it becomes is decided by the constraint imposed. No new theorem or law is claimed. Scope of this p...

Yuuki Yamagishi · 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.