arXiv Machine Learning August 12, 2026 By Sergi Masip, Gido M. van de Ven, Javier Ferrando, Tinne Tuytelaars

Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability

Read the original on arXiv Machine Learning →

arXiv:2601. 22012v3 Announce Type: replace Abstract: Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying mechanisms.

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

Jul 14

Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models

arXiv:2607. 09785v1 Announce Type: cross Abstract: Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unlabeled streams.

By Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen, Joachim Collin, Bart{\l}omiej Twardowski, Szymon {\L}ukasik, Tinne Tuytelaars

robotics efficiency multimodal benchmarks

arXiv AI

Jun 3

Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys

arXiv:2606. 02860v1 Announce Type: cross Abstract: Catastrophic forgetting is often framed as a representational problem: after sequential training, a model appears to lose the features that supported performance on earlier tasks.

By Archie Chaudhury

llms computer-vision safety

arXiv AI

Sep 1

On the Plasticity Collapse in Continual Machine Unlearning

The paper investigates continual machine unlearning, where models must forget data over time. It identifies a fundamental issue called plasticity collapse, where successive unlearning requests cause geometric constraints that saturate parameter space, leading to two failure modes: forward failure (reduced forgetting quality) and backward failure (re‑memorization). Experiments across architectures and datasets confirm that plasticity collapse is a pervasive problem in continual unlearning.

By Yingdan Shi, Xiang Xu, Kaize Ding, Alfred O. Hero, Ren Wang

computer-vision safety

arXiv Machine Learning

Jun 16

Understanding Cross-Modal Contributions in Continual Vision-Language Models: A Theoretical Perspective

arXiv:2606. 14883v1 Announce Type: cross Abstract: Continual vision-language models are commonly addressed through sequential fine-tuning; however, although this paradigm enables adaptation to new environments (tasks), it inherently emphasizes the contribution of previously learned environments (tasks) at the expense of the stability required to preserve previously acquired knowledge.

By Salimeh Sekeh, Mary Wisell

llms fine-tuning multimodal

arXiv Machine Learning

Jul 30

The Art of Not Forgetting A Local Learning Architecture for Continual Learning

arXiv:2607. 26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?

By Ashmith Atmuri, Yashaswini Rao Bhogarajula

llms benchmarks

arXiv AI

Aug 13

Representation Finetuning for Continual Learning

arXiv:2603. 11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams.

By Haihua Luo, Xuming Ran, Tommi K\"arkk\"ainen, Huiyan Xue, Zhonghua Chen, Qi Xu, Fengyu Cong

fine-tuning benchmarks

One email a morning, machine-written

Related stories

Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models

Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys

On the Plasticity Collapse in Continual Machine Unlearning

Understanding Cross-Modal Contributions in Continual Vision-Language Models: A Theoretical Perspective

The Art of Not Forgetting A Local Learning Architecture for Continual Learning

Representation Finetuning for Continual Learning