Skip to content

Category

small language model

3,366 papers

#small language model Open access Aug 2026

Zonal-Modular Architecture of Artificial Mind: from a Speech LLM to a Coordinated System of Specialized Zones

This paper analyzes the problem of the low practical efficiency of modern large language models (LLMs). We argue that the limiting factor is not a limit of the technology itself, but the organization of reasoning and the architectural role assigned to the language model. We claim no novelty for the "executor — overseer...

Dmitriy Borzov · 0 citations
#small language model Open access Aug 2026

Executable Memory and World Coupling: Code as Cognitive Interface in a Self-Modifying Simulation

Large language model (LLM) agents have recently explored executable memory—compiling agent memory into code snippets that an external LLM interprets at inference time. We argue that this paradigm remains tied to a single architectural choice: the executor is an external model, the memory is a personal profile, and the...

Yizhang Hu · 0 citations
#small language model Open access Aug 2026

Drude Was Right Because Two Errors Cancelled ── The Heat Capacity Too Large by 82.68 and the Squared Speed Too Small by 180.70 ── Their Product Is 2.1856, Against the Actual Discrepancy of 2.1932 ── [Paper 274]

Drude (1900) obtained the ratio of thermal to electrical conductivity in a metal from classical theory alone, and got a value close to measurement. This paper asks why he was right──the answer is not that the premises were correct. Two premises erred largely in opposite directions and very nearly cancelled on taking a...

Yuuki Yamagishi · 0 citations
#explainable ai Open access Aug 2026

One Sea Holds Three Lengths, Spanning a Factor of 4.39x10^4 ── All Contain the Coriolis Parameter, and Nothing Else in Them Overlaps ── The Bathtub Vortex Has Rossby Number 3232, and Seeing Rotation There Needs Flow Below 0.031 mm/s ── [Paper 291]

A rotating ocean has several characteristic lengths. Each is called “the length set by Coriolis.”This paper asks whether they are the same thing──the answer is that they are different things. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new mathematical theorem and no new...

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

"Forbidden" Means "Slower by a Factor of 7.62x10^7" ── Hydrogen's 2s->1s Does Not Fail to Happen; It Takes 0.1216 Seconds ── The 21 cm Line Takes 11 Million Years, Yet 10^60 Atoms Emit 2.9x10^45 Photons a Second ── [Paper 285]

A selection rule is written as “this transition is forbidden.”Yet forbidden transitions are actually observed. This paper asks what “forbidden” means as a number──the answer is a matter of rate. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new mathematical theorem and no n...

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

Only the Logarithm Adds ── +50% Followed by -50% Is Not 0% but -25% ── Repeating +/-10% Fifty Times Each Gives -39.50%, While the Naive Sum Answers 0% ── [Paper 292]

A “rate of return” looks like a quantity that can be added. This paper asks which way of writing it can──the answer is the log return alone. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new mathematical theorem and no new law is claimed──the relation between simple and log...

Yuuki Yamagishi · 0 citations
#explainable ai Open access Aug 2026

What Saturates Is Not the Earthquake but the Scale ── Measured by m_b, the 2011 Tohoku Earthquake's Energy Is Estimated at One 5623rd ── A Scale Saturates When the Source Duration Exceeds the Period It Observes ── [Paper 282]

“Magnitude” is not one thing. There are four──M_L, m_b, M_S, M_w──and all but M_w hit a ceiling for great earthquakes. This paper asks whether what hits the ceiling is the earthquake or the scale──the answer is the scale. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new ma...

Yuuki Yamagishi · 0 citations
#explainable ai Open access Aug 2026

One Sea Holds Three Lengths, Spanning a Factor of 4.39x10^4 ── All Contain the Coriolis Parameter, and Nothing Else in Them Overlaps ── The Bathtub Vortex Has Rossby Number 3232, and Seeing Rotation There Needs Flow Below 0.031 mm/s ── [Paper 291]

A rotating ocean has several characteristic lengths. Each is called “the length set by Coriolis.”This paper asks whether they are the same thing──the answer is that they are different things. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new mathematical theorem and no new...

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

LoMax: LLM‐Driven Local Code Optimization for MaxSAT Solvers

LoMax is presented, a plug‐and‐play framework that leverages an LLM to perform local code optimization for MaxSAT solvers, providing empirical evidence that LLM‐driven local code rewriting can improve the performance of industrial MaxSAT solvers in the evaluated settings.

Fan Gao, Yanhong Huang, Jian-Wen Li et al. · 0 citations
#small language model Review Open access Aug 2026

From Konigsberg's Bridges to Complex Networks: A Narrative Review of Graph Theory's Foundations, Landmark Theorems, and Applications

Graph theory began in 1736 as Euler's solution to the Konigsberg bridge problem and became mathematics' most versatile language for structure---in chemistry, sociology, computer science, and network science. This article presents a narrative review of the field's canonical line: Euler's 1736 paper, Kempe's 1879 four-co...

Zen Revista, 10 MATH · 0 citations
#small language model Open access Aug 2026

"Capacity" Is a Number Attainable Only at Infinite Length ── At Blocklength 100 Only 41.68% of the Capacity Is Usable, and Reaching 99.99% Takes 3.4x10^9 ── C Is a Supremum, Not a Maximum ── [Paper 304]

Shannon’s coding theorem says that below the channel capacity C the error can be made arbitrarily small. This paper asks whether C itself is attainable──the answer is not at any finite blocklength. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new mathematical theorem and n...

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

PARA: Perception, Action, Reasoning, Adaptation. Four Faculties an Institution Can Revoke

The fourth faculty is Adaptation. Any source rendering it as Reflection is in error, including sources by this author, and the distinction is not cosmetic: reflection is a private act with no external consequence, while adaptation writes to institutional memory, which is why it needs a guardrail and why misnaming it re...

Nabeel A. Khan · 0 citations

From tech blogs

See all →
MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

Microsoft Research Blog Oct 22, 2026

Flint-interactive: A language for creating interactive data visualizations

Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations 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.