Skip to content

Category

small language model

3,366 papers

#small language model Open access Aug 2026

Source-Preserving Prompt Augmentation and Category-Adaptive Inference for Qwen3-1.7B: A Prospective Seed-Replication Study

This preprint investigates whether a fixed compound inference intervention can improve the performance of a small language model without updating its parameters. The experimental program compares structured prompt replacement, natural-language rewriting, source-preserving semantic augmentation, and a category-adaptive...

Thibaud Peverelli · 0 citations
#small language model Open access Aug 2026

Source-Preserving Prompt Augmentation and Category-Adaptive Inference for Qwen3-1.7B: A Prospective Seed-Replication Study

This preprint investigates whether a fixed compound inference intervention can improve the performance of a small language model without updating its parameters. The experimental program compares structured prompt replacement, natural-language rewriting, source-preserving semantic augmentation, and a category-adaptive...

Thibaud Peverelli · 0 citations
#small language model Open access Aug 2026

"Conserved" Has Two Distinct Roots, and Noether Explains Only One ── Shorten the Pendulum and the Energy Rises by 2.000000 While E/omega Does Not Move ── What Separates Them Is Not Symmetry but Slowness ── [Paper 310]

This corpus has cited Noether’s theorem in 27 papers. This paper asks whether every conserved quantity comes from a symmetry──the answer is no. 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──adiabatic invariants, action var...

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

Reproducibility files for: CXRG-SVLM: A Parameter-Efficient Small Vision-Language Model for Multi-View Chest X-ray Report Generation in Resource-Constrained Environments.

This repository contains the official implementation, training and inference scripts, pre-extracted dataset splits (train/val/test), custom clinical entity evaluation metrics, and model weights for the CXRG-SVLM architecture. The pipeline integrates a frozen RAD-DINO medical vision encoder with a 4-bit quantized Qwen2....

Muhammad Fareed, Muhammad Awais Sattar · 0 citations
#small language model Open access Aug 2026

There Is Only One Kind of Constant You Can Ask "Has It Changed?" About ── Oklo Holds It Below 5.0x10^-18 per Year ── Six Decimal Places Beyond the Digit Eddington Argued Over ── [Paper 314]

Paper 10 established that only dimensionless numbers can be fine-tuned. This paper asks whether the same restriction applies to “has it changed”──the answer is it does. And one of them has actually been measured. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new mathematica...

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

One Number Sets the Limit of Forecasting ── Each Extra Day Costs 1.5874 Times the Initial Accuracy ── Observe 10 Times More Precisely and You Gain Only 4.98 Days ── [Paper 289]

That a weather forecast cannot reach beyond a certain horizon is due neither to missing equations nor to slow computers. This paper asks what sets the limit──the answer is one number, the error doubling time tau_d. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No new mathemati...

Yuuki Yamagishi · 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

Can AI Replace Humans? — How Human Knowledge Continues to Grow in the Era of Large Language Models

Recommendation algorithms determine what people see, and may also influence the perspectives through which people understand the world. As Large Language Models (LLMs) enter the domains of knowledge acquisition and information comprehension, this influence may extend further into human understanding, judgment, and mode...

ling liu · 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
#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
#explainable ai Open access Aug 2026

Can AI Replace Humans? — How Human Knowledge Continues to Grow in the Era of Large Language Models

Recommendation algorithms determine what people see, and may also influence the perspectives through which people understand the world. As Large Language Models (LLMs) enter the domains of knowledge acquisition and information comprehension, this influence may extend further into human understanding, judgment, and mode...

ling liu · 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.