arXiv Machine Learning August 11, 2026 By Yousef Abdi, Mohammad Asadpour, Yousef Seyfari

MAGIC-SSCIL: Manifold Anchoring and Geometric Incremental Calibration for Semi-Supervised Class Incremental Learning

Read the original on arXiv Machine Learning →

arXiv:2608. 07586v1 Announce Type: cross Abstract: Semi-supervised Class Incremental Learning (SSCIL) is a severe challenge for neural networks, and it is hardest in the exemplar-free setting where no past data may be stored.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jun 5

Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning

arXiv:2606. 05675v1 Announce Type: new Abstract: Continual learning (CL) seeks models that acquire new skills without erasing prior knowledge.

By Hongye Xu, Bartosz Krawczyk

rag benchmarks safety

arXiv Machine Learning

Jun 25

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

arXiv:2606. 25347v1 Announce Type: new Abstract: Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space.

By Hongye Xu, Bartosz Krawczyk

fine-tuning safety

arXiv AI

Jun 26

Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning

arXiv:2606. 27095v1 Announce Type: cross Abstract: Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task.

By Augustinas Ju\v{c}as, Yangchen Pan

computer-vision safety

arXiv Machine Learning

1d ago

Free-Flow Class-Incremental Learning: Towards Robust CIL under Variable Class Arrivals

arXiv:2604. 02765v2 Announce Type: replace Abstract: Class-incremental learning (CIL) is commonly evaluated under predefined schedules with fixed or nearly equal class increments, leaving irregular class-arrival scenarios underexplored.

By Zhiming Xu, Baile Xu, Jian Zhao, Furao Shen, Suorong Yang

safety

arXiv Machine Learning

Jun 5

Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss

arXiv:2606. 05695v1 Announce Type: new Abstract: Exemplar-free class-incremental learning (EFCIL) aims to acquire new classes over time without storing raw data.

By Hongye Xu, Bartosz Krawczyk

benchmarks

arXiv Machine Learning

Jul 1

TORA: Topological Representation Alignment for 3D Shape Assembly

arXiv:2604. 04050v2 Announce Type: replace-cross Abstract: Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which cross-part interactions should drive the motion.

By Nahyuk Lee, Zhiang Chen, Marc Pollefeys, Sunghwan Hong

llms benchmarks safety

Related stories

Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning

Free-Flow Class-Incremental Learning: Towards Robust CIL under Variable Class Arrivals

Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss

TORA: Topological Representation Alignment for 3D Shape Assembly