[2506.03719] On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

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

[2506.03719] On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity 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:2506.03719 (cs) [Submitted on 4 Jun 2025 ( v1 ), last revised 1 Dec 2025 (this version, v2)] Title: On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity Authors: Quentin Bertrand , Anne Gagneux , Mathurin Massias , Rémi Emonet View a PDF of the paper titled On the Clos

related reading

• [2404.19756] KAN: Kolmogorov-Arnold Networksarxiv.org
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• [2507.06187] The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gainsarxiv.org
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
• [2512.19428] Attention Is Not What You Needarxiv.org
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewarxiv.org
• [2506.09501] Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inferencearxiv.org
• [2503.11615v2] From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Settingarxiv.org
• [2508.12773] Online Ensemble Transformer for Accurate Cloud Workload Forecasting in Predictive Auto-Scalingarxiv.org
• [2505.06589v1] Optimal Transport for Machine Learnersarxiv.org
• [2505.12387] Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learningarxiv.org
• [2506.06194] Transformative or Conservative? Conservation laws for ResNets and Transformersarxiv.org