arXiv Machine Learning July 15, 2026 By Muhammad Haseeb, Salaar Masood, Muhammad Abdullah Sohail, Mohammad Fatim Shoaib, Muhammad Tahir

Mechanistic Evidence for Preserved-but-Misaligned Representations in Non-IID FedAvg

Read the original on arXiv Machine Learning →

arXiv:2512. 23043v2 Announce Type: replace Abstract: Federated Averaging (FedAvg) often degrades under non-IID client data, but it remains unclear whether this degradation reflects the loss of client-learned representations or a failure to use representations that are still present.

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 AI

Jun 29

Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning

arXiv:2605. 20282v3 Announce Type: replace-cross Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics.

By Zhenyu Yu, Yangchen Zeng, Chunlei Meng, Guangzhen Yao, Shuigeng Zhou

safety

arXiv AI

Jun 2

Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning

arXiv:2605. 20282v2 Announce Type: replace-cross Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics.

By Zhenyu Yu, Yangchen Zeng, Chunlei Meng, Guangzhen Yao, Shuigeng Zhou

safety

arXiv AI

Jun 11

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

arXiv:2606. 12138v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs.

By Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky, Daniil Laptev, Vadim Kurochkin, Daniil Gavrilov

arXiv AI

Aug 5

One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting

arXiv:2507. 07754v3 Announce Type: replace-cross Abstract: Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores.

By Jaeheun Jung, Bosung Jung, Suhyun Bae, Donghun Lee

benchmarks

arXiv Machine Learning

Jul 15

Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise

arXiv:2607. 12438v1 Announce Type: new Abstract: Deep networks trained with label noise often learn clean structure before memorizing corrupted labels.

By Satwik Bathula, Anand A. Joshi

llms computer-vision

arXiv Machine Learning

Sep 22

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

arXiv:2609.24379v1 Announce Type: cross Abstract: Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entan...

By Gautam Ranka, Shubham Santosh Pandere, Aiden Dsouza

llms efficiency safety

One email a morning, machine-written

Related stories

Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning

Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting

Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity