Search Results

Documents authored by Yang, Andy


Document
Theory of Neural Language Models (Dagstuhl Seminar 25282)

Authors: Pablo Barcelo, David Chiang, George Cybenko, Lena Strobl, and Andy Yang

Published in: Dagstuhl Reports, Volume 15, Issue 7 (2026)


Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 25282 "Theory of Neural Language Models". The seminar aimed to bring researchers together to lay a foundation for continued work on the theory of neural language models, focusing on questions including: How do transformers, RNNs, other NLMs, and their variants, compare with one another in expressivity and trainability? How do the successes and failures of NLMs predicted by theoretical models manifest in practice? What modifications, or what wholly new architectures, are suggested by the theory?

Cite as

Pablo Barcelo, David Chiang, George Cybenko, Lena Strobl, and Andy Yang. Theory of Neural Language Models (Dagstuhl Seminar 25282). In Dagstuhl Reports, Volume 15, Issue 7, pp. 22-52, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)


Copy BibTex To Clipboard

@Article{barcelo_et_al:DagRep.15.7.22,
  author =	{Barcelo, Pablo and Chiang, David and Cybenko, George and Strobl, Lena and Yang, Andy},
  title =	{{Theory of Neural Language Models (Dagstuhl Seminar 25282)}},
  pages =	{22--52},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2026},
  volume =	{15},
  number =	{7},
  editor =	{Barcelo, Pablo and Chiang, David and Cybenko, George and Strobl, Lena and Yang, Andy},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.15.7.22},
  URN =		{urn:nbn:de:0030-drops-257689},
  doi =		{10.4230/DagRep.15.7.22},
  annote =	{Keywords: Dagstuhl Seminar, Neural Networks, Language Models, Automata, Logic, Model Theory, Circuit Complexity}
}
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail