[2506.06194] Transformative or Conservative? Conservation laws for ResNets and Transformers

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2506.06194] Transformative or Conservative? Conservation laws for ResNets and Transformers Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2506.06194 (cs) [Submitted on 6 Jun 2025] Title: Transformative or Conservative? Conservation laws for ResNets and Transformers Authors: Sibylle Marcotte , Rémi Gribonval , Gabriel Peyré View a PDF of the paper titled Transformative or Conservative? Conservation laws for ResNets and Transformers, by Sibylle Marcotte and 2

related reading

• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Ilya 30u30arc.net
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• arxiv.org/pdf/2512.24880#page=3.56arxiv.org
• Cutting the Skip: Training Residual-Free Transformersarxiv.org
• bachlechner21a.pdfproceedings.mlr.press
• The Annotated Transformernlp.seas.harvard.edu
• Transformers from Scratche2eml.school
• Thinking like Transformersrush.github.io
• The Decade of Deep Learning | Leo Gaobmk.sh
• [2212.07677] Transformers learn in-context by gradient descentarxiv.org
• Residual neural network - Wikipediaen.wikipedia.org