Menu
View
Theme
Text size
The paper in your inbox every morning
Straight from the source · Glossary

The Tech Gazette

Scaling laws

Vol. I No. 26 Saturday, October 17, 2026 Closing 12:53 PM UTC · next edition 10:00 AM UTC

The observed, fairly predictable way a model's quality improves as its size, data and compute grow.

Read more at en.wikipedia.org →

In the news

  1. arXiv cs.AIOct 6, 2026Research
    Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements
  2. arXiv hep-exOct 5, 2026Research
    How to scale your HEP ML models: A recipe for robust architecture comparisons at scale
  3. Timothy B. Lee (Understanding AI)Oct 5, 2026Columns
    Why agent swarms could be the next “scaling law”
  4. arXiv cs.LGOct 1, 2026Research
    Universal interpolation for deep residual self-attention networks
  5. arXiv cs.LGSep 30, 2026Research
    Scaling Laws for Looped Mixture of Experts
  6. arXiv cs.CLSep 30, 2026Research
    How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text
  7. arXiv cs.LGSep 29, 2026Research
    When do data mixtures improve scaling laws? Insights from high-dimensional regression
  8. arXiv cs.LGSep 28, 2026Research
    ScAn-Bench: Evaluating Scaling Analysis Methodology
  9. arXiv cs.LGSep 23, 2026Research
    The Capability Manifold and ML Scaling Laws
  10. arXiv cs.LGSep 23, 2026Research
    A Scaling Study for fMRI Foundation Models