arXiv Machine Learning July 28, 2026 By Tao Zhang, Qixuan Fan, Yiyuan Liang, Yanjie Wang, Song Yan, Tian Tian, Jiahuan Zhou, Luxin Yan, Sheng Zhong, Xu Zou

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

Read the original on arXiv Machine Learning →

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

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

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

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 31

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation

arXiv:2603. 12055v3 Announce Type: replace-cross Abstract: Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and previous stages, allowing new-task supervision to induce geometric distortion.

By Chiyuan He, Zihuan Qiu, Fanman Meng, Runtong Zhang, Linfeng Xu, Qingbo Wu, Hongliang Li

llms efficiency multimodal benchmarks safety

arXiv AI

Jun 30

Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation

arXiv:2606. 30190v1 Announce Type: cross Abstract: Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity.

By Naeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer, Mukesh Prasad, Weiping Ding, Yew-Soon Ong

llms diffusion fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 31

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

arXiv:2607. 27372v1 Announce Type: new Abstract: The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages.

By Alexi Gladstone, Heng Ji, Yilun Du

diffusion benchmarks

arXiv Machine Learning

Jun 30

Prototype Latent World Model Replay for Class-Incremental Learning

arXiv:2606. 29465v1 Announce Type: new Abstract: Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones.

By Weizhi Nie, Hui Wang, Weijie Wang, Yuting Su

fine-tuning benchmarks

Related stories

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

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

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation

Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

Prototype Latent World Model Replay for Class-Incremental Learning