Our new paper on continual learning with no task boundaries

Interested in Continual (Lifelong) Learning? Come to the Workshop on Multi-Task and Lifelong Reinforcement Learning tomorrow (Saturday) @ ICML for posters and oral on how to rehearse on on older tasks efficiently!

Most continual learning approaches assume that training on a new task will cause equal interference over previously learned tasks. With "Maximally Interfered Retrieval" we relax this assumption by automatically rehearsing on tasks currently undergoing the most forgetting.

Our new continual learning survey with @matt_dl96 and まさな is now on arxiv. We compare 10 SOTA continual learning methods on 2 benchmarks. We investigate the effect of model capacity, regularization, task ordering and so much more. Check it out at: arxiv.org/abs/1909.08383

+ 8min video youtube.com/watch?v=wfb9UV… + code! github.com/optimass/Maxim…

We [EXCEPTIONALLY] extend the deadline of our workshop on "Theory of Continual Learning" (ICML'21) to June 11th (AoE) more information at: sites.google.com/view/cl-theory…

[Worskhop on Theory of Continual learning (ICML'21)] Thrilled to announce our awesome speaker line up: sites.google.com/view/cl-theory… You can ask questions to our speakers here: docs.google.com/forms/d/e/1FAI… Happening this Friday 23rd !🔥🚀

We are looking for excellent students for research internships on Continual Learning at Toyota Motor Europe. Please share and contact me if you are interested. social.icims.com/viewjob/pt1669…

This is why we need continual learning ;)

If you are working on continual learning with foundation models and you have something cool to share, please consider submitting to our NeurIPS workshop sites.google.com/u/0/d/1VBppSNb…

If you are at European Conference on Computer Vision #ECCV2026 and interested in a postdoc position on efficient multimodal models, please ping me for a chat.

A gating autoencoder that learns a representation for the task, and at test time automatically forwards the sample to the relevant expert x.com/naiveoculus/st…

We propose a new solution to the catastrophic forgetting when learning tasks sequentially using task autoencoders. arxiv.org/pdf/1704.01920…

Given a limited model capacity and unlimited evolving data, it is not possible to preserve all the previous knowledge that an agent has learned. How about learning what (not) to forget instead? That's what we humans do and our method aims at arxiv.org/abs/1711.09601