Hugging Face Trending Papers June 23, 2026

The Gentle Collapse: Distributional Metrics for Continual Learning

Read the original on Hugging Face Trending Papers →

Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapses discretely at task boundaries, hiding the internal structure of what is being forgotten.

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

arXiv Machine Learning

Jun 25

The Gentle Collapse: Distributional Metrics for Continual Learning

arXiv:2606. 25165v1 Announce Type: new Abstract: Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not.

By Ahmed Anwar, Andreas Wagner, Federico Raue, Tobias Nauen, Andreas Dengel

arXiv Machine Learning

Jun 5

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

arXiv:2606. 06032v1 Announce Type: new Abstract: Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning.

By Ayushman Trivedi, Bhavika Melwani

arXiv Machine Learning

Jun 9

Evaluating the Impact of Task Granularity on Catastrophic Forgetting in Continual Learning

arXiv:2606. 08013v1 Announce Type: new Abstract: Catastrophic forgetting, the abrupt loss of previously acquired knowledge upon learning new information, remains the central challenge in Continual Learning.

By Emre Alyamac, Himanshu Janmeda, Shashwat Krishna, Yash Vijay

arXiv Machine Learning

Jun 25

Erased, but Not Gone: Output Forgetting Is Not True Forgetting

arXiv:2606. 25001v1 Announce Type: new Abstract: Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference.

By Teresa Pui Yee Yong, Win Kent Ong, Chee Seng Chan

arXiv Machine Learning

1d ago

Geometry of Forgetting: Representation Flux in Continual Learning

arXiv:2608. 15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks.

By Maksim A. Kazanskii

benchmarks

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

Related stories

The Gentle Collapse: Distributional Metrics for Continual Learning

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

Evaluating the Impact of Task Granularity on Catastrophic Forgetting in Continual Learning

Erased, but Not Gone: Output Forgetting Is Not True Forgetting

Geometry of Forgetting: Representation Flux in Continual Learning

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