Hugging Face Trending Papers July 22, 2026

The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networks

Read the original on Hugging Face Trending Papers →

Additive models buy interpretability by forbidding feature interactions, a constraint that neural instantiations enforce architecturally. We introduce the quadrilateral loss, a differentiable penalty that treats additivity as a measurable behavior instead: a second-order mixed difference on pairs of training points swapping one coordinate, which vanishes if and only if the coordinate carries no interaction, remains informative for piecewise-linear networks, and equals in expectation the per-coordinate interaction mass of the interventional Shapley-GAM.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

safety

arXiv AI

Jul 23

The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networks

arXiv:2607. 20201v1 Announce Type: cross Abstract: Additive models buy interpretability by forbidding feature interactions, a constraint that neural instantiations enforce architecturally.

By Antonio Di Cecco

safety

arXiv AI

Jul 14

Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization

arXiv:2607. 09967v1 Announce Type: cross Abstract: Many neural networks operations have a multiplicative nature rather than additive: halving or doubling a norm are analogous relatively but require unequal optimization distances when taking linear steps.

By Ethan Smith

llms

arXiv AI

Jul 14

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs

arXiv:2607. 10803v1 Announce Type: cross Abstract: Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability.

By Shrestha Datta, Hongfu Liu, Anshuman Chhabra

llms efficiency safety

arXiv Machine Learning

Jun 29

Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks

arXiv:2606. 27759v1 Announce Type: new Abstract: Training binary neural networks (BNNs) from scratch is dominated by the straight-through estimator (STE), whose forward/backward mismatch produces severe accuracy degradation as networks deepen.

By Evan Gibson Smith, Bashima Islam

fine-tuning

arXiv Machine Learning

Jun 30

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

arXiv:2606. 29951v1 Announce Type: new Abstract: Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models.

By Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, P{\aa}l Halvorsen

benchmarks safety

arXiv AI

Jul 23

In-Run Data Shapley for Adam Optimizer

arXiv:2602. 00329v4 Announce Type: replace-cross Abstract: Reliable data attribution is essential for mitigating bias and reducing computational waste in modern machine learning, with the Shapley value serving as the theoretical gold standard.

By Meng Ding, Zeqing Zhang, Di Wang, Lijie Hu

efficiency safety

Related stories

The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networks

Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs

Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

In-Run Data Shapley for Adam Optimizer