arXiv Machine Learning June 11, 2026 By David Young, Swan Yi Htet

Energy-Conserved Neural Pipelines: Attenuating Error Propagation in Modular Neural Networks via Physical Conservation Constraints

Read the original on arXiv Machine Learning →

arXiv:2606. 11341v1 Announce Type: new Abstract: Modular neural network pipelines suffer from error compounding: noise at any module boundary propagates and potentially amplifies through subsequent modules.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 16

Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks

arXiv:2607. 13380v1 Announce Type: new Abstract: Predictive Coding (PC) offers a biologically motivated alternative to backpropagation via local weight updates, yet routing error between layers still relies on an autograd Jacobian-transpose ($J^\top$) product - the last non-local operation in PC.

By Junlong Shen, Xingyu Li

benchmarks

arXiv Machine Learning

Sep 1

SDF-Aware Weighting: Adaptive Eikonal Regularisation for Three-Dimensional Level-Set Physics-Informed Neural Networks

arXiv:2608.08322v2 Announce Type: replace-cross Abstract: Adaptive loss-balancing schemes for physics-informed neural networks rest on a premise that every residual should be driven to zero. For leve...

By Muhammad Akbar Khan

benchmarks

arXiv AI

4d ago

Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant

arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...

By Amirhossein Yousefiramandi

arXiv AI

Jun 17

Conservation Laws for Modern Neural Architectures

arXiv:2606. 17816v1 Announce Type: cross Abstract: Understanding gradient descent dynamics is key to explaining the success of over-parameterized models, where implicit bias manifests through conservation laws in gradient flow.

By Viet-Hoang Tran, Vinh Khanh Bui, Tan Lai Ngoc, Nam Nguyen, Tuan Dam, Tan M. Nguyen

safety

arXiv Machine Learning

Jun 24

DREG: A Layer-Wise Jacobian Regularization as a General-Purpose Penalty

arXiv:2606. 23942v1 Announce Type: new Abstract: We present a large-scale empirical study isolating the contributions of the Derivative Regularization penalty (DREG).

By Rowan Martnishn

llms nlp benchmarks safety

arXiv AI

Jun 11

A Physics-Inspired Optimizer: Velocity Regularized Adam

arXiv:2505. 13196v3 Announce Type: replace-cross Abstract: We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its stabilizing effects on various system dynamics.

By Pranav Vaidhyanathan, Lucas Schorling, Natalia Ares, Maike Osborne

llms computer-vision benchmarks

One email a morning, machine-written

Related stories

Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks

SDF-Aware Weighting: Adaptive Eikonal Regularisation for Three-Dimensional Level-Set Physics-Informed Neural Networks

Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant

Conservation Laws for Modern Neural Architectures

DREG: A Layer-Wise Jacobian Regularization as a General-Purpose Penalty

A Physics-Inspired Optimizer: Velocity Regularized Adam