arXiv Machine Learning June 5, 2026 By Hongye Xu, Bartosz Krawczyk

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

Read the original on arXiv Machine Learning →

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

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.

benchmarks

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

Jul 28

Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning

arXiv:2607. 22994v1 Announce Type: cross Abstract: Class-incremental learning (CIL) requires models to continuously acquire new knowledge while avoiding catastrophic forgetting.

By Tao Zhang, Qixuan Fan, Yiyuan Liang, Yanjie Wang, Song Yan, Tian Tian, Jiahuan Zhou, Luxin Yan, Sheng Zhong, Xu Zou

diffusion benchmarks safety

arXiv AI

Jun 16

When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning

arXiv:2606. 15695v1 Announce Type: cross Abstract: Federated class-incremental learning (FCIL) becomes substantially harder when clients observe different label subsets, progress through tasks at different stages, and provide uneven supervision for the same semantic concepts.

By Thinh T. H. Nguyen, Khoa D. Doan, Binh T. Nguyen, Danh Le-Phuoc, Kok-Seng Wong

agents benchmarks safety

arXiv AI

Jun 18

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

arXiv:2606. 19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets.

By Ruishan Fang, Siyuan Lu, Chenyi Zhuang, Tao Lin

agents reinforcement-learning

arXiv Machine Learning

Sep 1

One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning

arXiv:2608.31096v1 Announce Type: cross Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while...

By Yunxiang Fu, Meng Lou, Yizhou Yu

fine-tuning

arXiv AI

Sep 7

MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning

MePo++ is a post‑training framework designed for general continual learning (GCL) that unifies representation refinement and reconciliation. It introduces MetaPrep, which enhances representation plasticity via unsupervised meta‑refinement on pseudo continual sequences, and StreamAlign, which maintains stability by reconciling online features with a stable pretrained geometry. Experiments across various pretrained models, datasets, and continual learning baselines show that MePo++ consistently improves performance in PTM‑based GCL.

By Guanglong Sun, Kanglei Zhou, Liyuan Wang, Qi Cheng, Hongwei Yan, Shuang Cui, Hang Su, Jun Zhu, Yi Zhong

safety

One email a morning, machine-written

Related stories

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

Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning

When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning

MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning