arXiv Machine Learning July 23, 2026 By Denis Gueyffier (ONERA -- Institut Polytechnique de Paris)

Hard Guarantees at a Measured Price: Entropy-Stable Learned Finite Volumes for Compressible Flow

Read the original on arXiv Machine Learning →

arXiv:2607. 20171v1 Announce Type: cross Abstract: Learned solvers for compressible flow are usually compared to classical methods at equal mesh resolution rather than at equal computational cost, and they typically offer no guarantee that their solutions remain physically admissible.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 6

Guarantees by Construction for Learned Finite Volume Schemes on Steady Supersonic Flow

arXiv:2607. 20171v3 Announce Type: replace-cross Abstract: A second order finite volume scheme rests on two local quantities: a gradient reconstructed in each cell, and a limiter which scales it down where the reconstruction would overshoot.

By Denis Gueyffier (ONERA -- Institut Polytechnique de Paris)

arXiv AI

Jul 24

When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers

arXiv:2607. 20594v1 Announce Type: cross Abstract: When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm?

By Tong Zhang, Junhao Hu, Yun Peng, Tao Xie

llms benchmarks

arXiv Machine Learning

5d ago

Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation

arXiv:2606. 21253v2 Announce Type: replace Abstract: Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally.

By Jianwei Lou (RailMind Systems, Neuss, Germany)

agents computer-vision

arXiv Machine Learning

Jul 30

When Do Learned Diffusion Proposals Help Constraint Solving? A Controlled Study on Continuous Algebraic Systems

arXiv:2607. 27169v1 Announce Type: new Abstract: Solving a continuous algebraic constraint system requires two decisions: which values satisfy the constraints, and which structural augmentation renders an unsolvable system solvable.

By Quang Bui, Sparsh Roy, Akash Gundimeda, Davin Yin

diffusion robotics

arXiv AI

Jun 11

Signed Compression Progress on a Sealed Audit is Goodhart-Resistant

arXiv:2606. 11417v1 Announce Type: cross Abstract: Compression progress is a long-standing proposal for intrinsic motivation: reward an agent when its world model becomes better at predicting or compressing experience.

By Ayush Mittal, Dhruv Gupta

agents

arXiv Machine Learning

Jul 8

Level-Crossing Density as a Mesh-Free High-Frequency Auxiliary Loss for Implicit Neural Representations

arXiv:2607. 05815v1 Announce Type: new Abstract: The Minkowski functionals of a field's excursion sets -- area, boundary measure, and Euler characteristic -- describe its level-set morphology; the Euler characteristic is the cheapest handle on topology.

By Gunner Levi Howe

benchmarks

Related stories

Guarantees by Construction for Learned Finite Volume Schemes on Steady Supersonic Flow

When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers

Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation

When Do Learned Diffusion Proposals Help Constraint Solving? A Controlled Study on Continuous Algebraic Systems

Signed Compression Progress on a Sealed Audit is Goodhart-Resistant

Level-Crossing Density as a Mesh-Free High-Frequency Auxiliary Loss for Implicit Neural Representations