arXiv Machine Learning August 18, 2026 By Zhiming Xu, Baile Xu, Jian Zhao, Furao Shen, Suorong Yang

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

Read the original on arXiv Machine Learning →

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.

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 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 7

DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised

arXiv:2311. 07461v3 Announce Type: replace Abstract: Autonomous systems (AS) often rely on Deep Neural Network (DNN) classifiers to operate in complex and dynamically changing environments.

By Abanoub Ghobrial, Kerstin Eder

agents fine-tuning

arXiv Machine Learning

Jun 11

RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning

arXiv:2606. 11761v1 Announce Type: new Abstract: Dynamic data pruning techniques aim to reduce computational cost while minimizing information loss by periodically selecting representative subsets of input data during model training.

By Atif Hassan, Swanand Khare, Jiaul H. Paik

fine-tuning efficiency benchmarks

Hugging Face Trending Papers

Jul 20

Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning

Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch, pre-trained model (PTM) can easily adapt to a new task with fine-tuning.

fine-tuning benchmarks

arXiv Machine Learning

Aug 5

When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning

arXiv:2602. 00573v2 Announce Type: replace Abstract: Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowledge.

By Zheng Zhang, Tao Hu, Xueheng Li, Yang Wang, Rui Li, Jie Zhang, Chengjun Xie

benchmarks

Related stories

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

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

DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised

RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning

Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning

When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning