method · first seen 8 Oct 2026
minimum description length
Also: MDL
A principle selecting models that minimise the combined cost of describing the model and the data.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Latent Core Tokenizer: Compress, but MeaningfullyPapers · 8 Oct 2026 · Felermino D. M. A. Ali, Millicent Ochieng, Ogbemi Ekwejunor-Etchie, Ade Famoti,…
- When Thoughts Become Memory: Unifying In-Context Learning and Fine-TuningPapers · 21 Oct 2026 · Leon Chlon, Julie Huang
- Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are StatisticalPapers · 23 Oct 2026 · Wenbin Mao, Pei Zou
- Interpretable neural equation learning for high-dimensional materials dataPapers · 27 Oct 2026 · Philip Jacobson, Prasad Iyer, Remi Dingreville, Saaketh Desai
Latest sources
- Interpretable neural equation learning for high-dimensional materials dataPapers · 27 Oct 2026 · Philip Jacobson, Prasad Iyer, Remi Dingreville, Saaketh Desai
- Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are StatisticalPapers · 23 Oct 2026 · Wenbin Mao, Pei Zou
- When Thoughts Become Memory: Unifying In-Context Learning and Fine-TuningPapers · 21 Oct 2026 · Leon Chlon, Julie Huang
- Latent Core Tokenizer: Compress, but MeaningfullyPapers · 8 Oct 2026 · Felermino D. M. A. Ali, Millicent Ochieng, Ogbemi Ekwejunor-Etchie, Ade Famoti,…