[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

• [2212.07677] Transformers learn in-context by gradient descentarxiv.org
• [2404.19756] KAN: Kolmogorov-Arnold Networksarxiv.org
• [2512.19428] Attention Is Not What You Needarxiv.org
• [2508.12773] Online Ensemble Transformer for Accurate Cloud Workload Forecasting in Predictive Auto-Scalingarxiv.org
• [2501.18322v1] A Unified Perspective on the Dynamics of Deep Transformersarxiv.org
• [2505.12387] Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learningarxiv.org
• [2505.06589v1] Optimal Transport for Machine Learnersarxiv.org
• [2305.18654] Faith and Fate: Limits of Transformers on Compositionalityarxiv.org
• [2405.07987] The Platonic Representation Hypothesisarxiv.org
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• [2503.09829] SE(3)-Equivariant Robot Learning and Control: A Tutorial Surveyarxiv.org
• [2506.03719] On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticityarxiv.org