<div dir="ltr"><div class="gmail-gs" style="margin:0px;min-width:0px;padding:0px 0px 20px;width:auto;font-family:"Google Sans",Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:medium"><div class="gmail-"><div class="gmail-ii gmail-gt" id="gmail-:1d0" style="direction:ltr;margin:8px 0px 0px;padding:0px;font-size:0.875rem;overflow-x:hidden"><div id="gmail-:y7" class="gmail-a3s gmail-aiL" style="direction:ltr;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;font-size-adjust:none;font-kerning:auto;font-feature-settings:normal;font-stretch:normal;font-size:small;line-height:1.5;font-family:Arial,Helvetica,sans-serif;overflow:auto hidden"><div dir="ltr"><p style="color:rgb(0,0,0)">Dear all,</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal">We are excited to bring you the second speaker of the monthly CoLLAs Seminar Series, which has an excellent line-up of speakers from around the world: <a href="https://lifelong-ml.cc/seminar" target="_blank">https://lifelong-ml.cc/seminar</a> </p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal">With this series, we aim to bring together researchers working on continual, lifelong, and adaptive machine learning to share new ideas, and foster community-wide dialogue!</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal">Our second talk will be by <b>Rahaf Aljundi</b> on <b>June 10 at 10:00 AM CET</b>.</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal"><b>Title</b>: Towards Continuous Accumulation of Knowledge and Experience</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal"><b>Abstract</b>: Continual learning enables models to adapt to streaming data, targeting knowledge accumulation, and avoiding catastrophic forgetting. Continual learning research has focused on continual parameter updates; however, forgetting and learning instability always seem unavoidable, rendering continual learning a far‑fetched problem. On the other hand, in‑context learning offers a complementary path to frequent parameter updates. In this talk, I argue that efficient, continuous adaptation needs not occur solely in parameter space. I will show how memory‑based mechanisms enable rapid adaptation and present some of my previous and recent continual learning works, then discuss how combining fast, memory‑driven updates with slow model consolidation could shape the future of continual learning.</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal"><b>Speaker bio</b>: Rahaf Aljundi is a research scientist at Toyota Motor Europe. She is interested in building models that can keep learning (given any source of supervision), can tell when a novel input is provided and further point at instances that require annotation. This includes the topics of continual learning (incremental learning, lifelong learning), novelty detection (out of distribution, anomaly detection), active learning and also domain adaptation. She has obtained her PhD degree from KU Leuven university (Belgium) where she extensively worked on the topic of continual learning.</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal"><b>Zoom</b>: <a href="https://polymtl-ca.zoom.us/j/84066718835?pwd=2cpVMN2XjRXyZrngOFBJSO3Fwifywo.1" target="_blank">https://polymtl-ca.zoom.us/j/84066718835?pwd=2cpVMN2XjRXyZrngOFBJSO3Fwifywo.1</a></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal">We look forward to seeing you there!</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal">Best regards,</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal;min-height:15px"><br></p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal">Sarath Chandar</p><p style="font-size:13px;margin:0px;line-height:normal;font-family:"Helvetica Neue";font-size-adjust:none;font-kerning:auto;font-variant-alternates:normal;font-variant-numeric:normal;font-variant-east-asian:normal;font-feature-settings:normal">On behalf of the CoLLAs Seminar Organizers</p></div><div class="gmail-yj6qo"></div><div class="gmail-adL"></div></div></div><div class="gmail-WhmR8e" id="gmail-avWBGd-335" style="clear:both"></div></div></div><br class="gmail-Apple-interchange-newline"></div>