Skip to content

Category

small language model

3,573 papers

#small language model Open access Sep 2026

CAMS Protocol R (CAMS-R-2026-001): preregistration, single-run results, and rubric erratum final

Protocol F (CAMS-F-2026-001): Design Rationale Companion to preregistration_F_draft.json — 2026-09-20 Status: DRAFT. The forecast file does not exist yet; no outcome-year scoring has begun. Protocols R and R2 answered does the relational pattern generalise? — twice, under lock and key. Protocol F asks the harder questi...

Kari McKern · 0 citations
#small language model Open access Sep 2026

Failing to Have a Transition for Want of Size Is Not the Same as Failing for Want of Dimension ── The free energy of the one-dimensional Ising model shows no jump in its second derivative at finite size (a largest step of 0.282856 at n=64) ── taking the limit is necessary for a transition, not sufficient ── [Paper 502]

The absence of a phase transition is put down to the system being finite. This paper shows that a system can fail to have one even in the thermodynamic limit──the one-dimensional Ising model, whose largest step stays at 0.510568. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law...

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

The Charter of the United Martian States: A Proposed Constitution for the Future Settlements on Mars

Abstract This document presents a complete constitutional framework for a future human society on Mars. The Charter of the United Martian States is a confederative instrument designed for a small, dispersed, high-risk frontier environment in which sovereign constituent polities voluntarily cooperate under strict limits...

Thomas Gangale · 0 citations
#small language model Open access Sep 2026

Window Theory • AI — Paper 0: Prologue

Window Theory - AI (wtAI): A Falsifiable Framework for Flexibility-Fragility Coupling in Large Language Models This is a six-part research series examining a structural pattern in decoder-based next-token-prediction systems deployed as dialogue and instruction agents. It is written for readers with a background in mach...

Wai-Hung (Pan) Tam · 0 citations
#small language model Open access Sep 2026

Voting, Validation, and Vulnerability in Local Language Model Penetration Testing An Empirical Study of Module Selection Under Adversarial Evidence

Small local language models are attractive for privacy-preserving penetration-testing assistants, but their module choices must remain reliable when target-controlled banners contain misleading or instruction-like text. We evaluate module selection in three experiments on an Apple M2 system with 8 GB of memory. A verif...

Piyush Shukla · 0 citations
#small language model Open access Sep 2026

MOME: Metamorphic Evidence as a Runtime Reliability Signal for Small Language Models

A black-box, label-free runtime gate for quantized small language models. Each problem is perturbed in two directions by rule -- a restatement whose answer must hold and an edit whose answer must change -- and the responses form a metamorphic fingerprint that a fixed predictor turns into a serve/verify/decline decision...

Bongjin Jung, Joongho Chang · 0 citations
#small language model Open access Sep 2026

Zeno's Four Paradoxes Do Not Share a Single Resolution ── the dichotomy falls to a convergent series, Achilles to an infinite sum, the arrow to the limit of a difference quotient and the stadium to a discrete space ── four paradoxes, four different pieces of mathematics ── [Paper 519]

Zeno’s paradoxes are often said, all together, to have been settled by the calculus. What this paper shows is that the four fall to four different tools, and that one of them does not fall to the calculus at all. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──the s...

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

The New Balance of Leverage: How Geopolitical Diversification Redefined the Canada-US Relationship

DESCRIPTION The New Balance of Leverage: How Geopolitical Diversification Redefined the Canada-US Relationship is an interdisciplinary examination of the changing economic, diplomatic, institutional, monetary, industrial, and security relationship between Canada and the United States during a period of heightened trade...

Michael James Arnold · 0 citations
#small language model Open access Sep 2026

Zeno's Four Paradoxes Do Not Share a Single Resolution ── the dichotomy falls to a convergent series, Achilles to an infinite sum, the arrow to the limit of a difference quotient and the stadium to a discrete space ── four paradoxes, four different pieces of mathematics ── [Paper 519]

Zeno’s paradoxes are often said, all together, to have been settled by the calculus. What this paper shows is that the four fall to four different tools, and that one of them does not fall to the calculus at all. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──the s...

Yuuki Yamagishi · 0 citations
#diffusion models Open access Sep 2026

The 2.5 in the Viscosity of a Suspension Comes Not from the Volume of the Particles but from the Stress They Place on the Flow Outside ── for the Stokes solution of a sphere in a uniform straining flow, the surface integral of the stress over the sphere (the stresslet) is 20π/3 times viscosity, radius cubed and strain, and dividing by the particle volume 4π/3 gives 2.5; solving viscosity and diffusion for two unknowns, a change of the coefficient from 1 to 2.5 moves Avogadro's number by a factor 1.581139 ── the separator is whether one counts the volume inside the particle or the stress outside it ── [Paper 1024]

A liquid with small spheres mixed in at volume fraction φ has, when dilute, (1 + 2.5φ) times its original viscosity. Einstein wrote the coefficient as 1 in his 1906 doctoral thesis and corrected it to 2.5 in 1911. This paper checks the Stokes solution for a sphere in a uniform straining flow by symbolic computation, ob...

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

precis-mcp: a Model Context Protocol server for papers, documents, and agent state

precis-mcp is a Model Context Protocol (MCP) server that gives language-model agents a small, uniform API for reading, writing, and searching across scientific papers, documents, personal state, code, and cached tool calls. Small-model-friendly (7B-class agents are the design target), it exposes a handful of typed verb...

Reto Stamm · 0 citations
#small language model Open access Sep 2026

Comprehension as Compliance: How Grounded Content, Not Form, Moves Small Language Models to Act, and Where It Does Not

A small language model, given a task prefixed with a description of a recurring decision, will often recognize the decision and fail to act on it. This paper draws together a program of studies on that effect and states what drives it. The effect is carried by the content of the description, not by its form: a plain im...

Sophie Neilson · 0 citations

From tech blogs

See all →

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