Sign in

Martin Mundt

@martinmundt.bsky.social
306 followers 414 following 38 posts

Professor for Lifelong Machine Learning @ Uni Bremen | OWL-ML Lab: owl-ml.com | Board @ ContinualAI | QueerInAI | CoLLAs 2026 Program Chair | He/him 🏳️‍🌈🇪🇺

PostsRepliesMedia
Martin Mundt @martinmundt.bsky.social · 05/07/2026
On my way to #ICML2026 Drop a message if you want to meet or stop by & check out: 1. Our work “Modular Memory is the Key to Continual Learning Agents” arxiv.org/abs/2603.01761 on Thursday 9th 2. Our workshop “Continual Adaptation at Scale: Towards Sustainable AI” cats-icml.github.io on Friday 10th
arxiv.org
Position: Modular Memory is the Key to Continual Learning Agents
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundam...
0160
Reposted by Martin Mundt
ACM FAccT @facct.bsky.social · 25/06/2026
Welcome to the #FAccT2026 conference, kicking off today! Bienvenue à Montréal! 🇨🇦 We're pleased to share this year's Best Paper Awards, as well as Best Paper Honorable Mentions! Congratulations to all the authors! 👏
facct-blog.github.io
Announcing Best Paper Awards
The Best Paper Award Committee was chaired this year by Suresh Venkatasubramanian and included eight Area Chairs: William Agnew, Sebastian Benthall, Toon Calders, Shion Guha, Kate Kaye, Samir Passi, a...
081
Reposted by Martin Mundt
Pranav A @pranav-nlp.bsky.social · 25/06/2026
Work is here: arxiv.org/abs/2606.11021, done with @dippedrusk.com, @martinmundt.bsky.social, @arjunsubgraph.bsky.social, @jordant.bsky.social, @willie-agnew.bsky.social, @dchechel.bsky.social, Franziska Sofia Hafner, @a-lauscher.bsky.social.
arxiv.org
Making a Name for Myself: On Academic Naming Policies and their Impact
In academic publishing, names connect scholars to their work. When scholars change their names, including for marriage, academic recognition, or gender transition, they may lose credit for past public...
042
Reposted by Martin Mundt
Pranav A @pranav-nlp.bsky.social · 25/06/2026
I will be presenting our work titled "Making a Name for Myself: On Academic Naming Policies and their Impact" this week at #FAccT2026. This paper talks about why names matter, why name change policies are important, how people benefit from it and what's still left to do.
Making a Name for Myself: On Academic Naming Policies and their
Impact
A PRANAV, Trustworthy AI Lab, University of Hamburg, Germany
VAGRANT GAUTAM, Heidelberg Institute for Theoretical Studies, Germany
MARTIN MUNDT∗
, University of Bremen, Germany
JORDAN TAYLOR∗
, Carnegie Mellon University, USA
ARJUN SUBRAMONIAN∗
, Queer in AI, USA
FRANZISKA SOFIA HAFNER∗
, University of Oxford, United Kingdom
DANIEL CHECHELNITSKY∗
, Carnegie Mellon University, USA
WILLIAM AGNEW∗
, Carnegie Mellon University, USA
ANNE LAUSCHER∗
, Trustworthy AI Lab, University of Hamburg, Germany
1328
Reposted by Martin Mundt
ACM FAccT @facct.bsky.social · 24/06/2026
Very important updates from our #FAccT2027 Program Chairs. Our next reviewing cycle will run on a different schedule from previous years. ⚠️ Abstract Deadline: Oct 27, 2026 ⚠️ Paper Deadline: Nov 3, 2026 Please read this blog post from the PCs for more info: facct-blog.github.io/2026-06-24/s...
facct-blog.github.io
Update to ACM FAccT Submission Timeline Beginning in 2027
Dear FAccT community, We are writing to share an important update to the ACM FAccT submissions timeline beginning with the 2027 conference cycle.
0149
Reposted by Martin Mundt
Queer in AI @queerinai.com · 12/06/2026
Come hang out with us at our FAccT bar social in a couple of weeks! Find more information at queerinai.com/facct-2026 🥂
Image with Queer in AI logo, FAccT logo, and the following text: "FAccT 2026 Bar Social. Thu, June 25 6:30 - 9:00 pm EDT. queerinai.com/facct-2026".
083
Martin Mundt @martinmundt.bsky.social · 02/05/2026
If you are currently at #AISTATS2026 then check out our work: “Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories” Beyond just OOD detection, we show how to distinguish different kinds of shift! arxiv.org/abs/2510.17381
030
Martin Mundt @martinmundt.bsky.social · 30/04/2026
Our position paper “Modular Memory is the Key to Continual Learning Agents” (arxiv.org/abs/2603.01761) has been accepted to #ICML2026 @icmlconf.bsky.social as a spotlight! 🎊 Read for a modern perspective on memory, continual learning, and sustainable adaptation at foundation model scale!
0173
Martin Mundt @martinmundt.bsky.social · 09/04/2026
Submit your work to our Continual Adaptation at Scale: Towards Sustainable AI Workshop @icmlconf.bsky.social #ICML2026: cats-icml.github.io Topics span a range of adaptation across the lifecycle (scale, efficiency, multimodal, alignment, forgetting) to drive sustainable AI! Deadline: April 30
041
Martin Mundt @martinmundt.bsky.social · 04/03/2026
Following our @dagstuhl.de seminar on Continual Learning in the Foundation Model Era, we are now sharing a roadmap! In summary, we view modular memory design as the missing piece to combine the capabilities of In-Weight & In-Context Learning for adaptation at scale: arxiv.org/abs/2603.01761
arxiv.org
Modular Memory is the Key to Continual Learning Agents
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundam...
1110
Martin Mundt @martinmundt.bsky.social · 04/12/2025
The 5th edition of the Conference on Lifelong Learning Agents is going to Romania in 2026 & I'm happy to serve as program chair We've just put the CfP online ⬇️ & we're particularly excited to broaden the scope to all facets of adaptation of ML models. Please check out these exciting additions!
031
Martin Mundt @martinmundt.bsky.social · 06/10/2025
Wonder how LLMs learn over long time horizons & how hate-checks deal with time? Look at our new work "Chronoberg": an open-source dataset spanning 250 years of books with analysis of shifts in meaning & continual learning of LLMs: arxiv.org/pdf/2509.22360 huggingface.co/datasets/spa...
051
Martin Mundt @martinmundt.bsky.social · 16/09/2025
🎉"Aligning generalization between humans and machines" (w/ 25 incredible authors) is out now in #Nature Machine Intelligence: www.nature.com/articles/s42... In short, we identified interdisciplinary commonalities & differences with respect to notions of, methods for, & evaluation of generalization
060
Martin Mundt @martinmundt.bsky.social · 19/08/2025
Feeling really inspired after @collasconf.bsky.social: wonderful keynotes, exceptionally talented early-career spotlights & interactions that mattered! And of course our own oral presentation as well :) Very excited to be the next program chair & ensure its success for CoLLAs in Romania next year!
030
Martin Mundt @martinmundt.bsky.social · 11/08/2025
Just arrived in Philadelphia for @collasconf.bsky.social Very excited about a fantastic program! I’ll be around all week, but feel free to drop me a message or catch me directly at the debate on Monday morning, after our oral presentation on Tuesday, or in any of the poster sessions
030
Reposted by Martin Mundt
collasconf.bsky.social @collasconf.bsky.social · 05/08/2025
🎉 Announcing the winners of the #CoLLAs2025 Early-Career Spotlight Program! These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI. 👇 A thread introducing their work & talks. #AI #MachineLearning #ContinualLearning #LifelongLearning
154
Reposted by Martin Mundt
collasconf.bsky.social @collasconf.bsky.social · 31/07/2025
🧠 Don't miss the tutorials at #CoLLAs2025! We’re excited to host two deep dives into the theory and practice of lifelong learning: 📍Information-Theoretic Measures for Multi-Expert FM Adaptation 📍Mathematics of Continual Learning Details below 👇
123
Martin Mundt @martinmundt.bsky.social · 15/07/2025
I'm not at #ICML2025 myself, but @florianbusch.bsky.social & Roshni are presenting our spotlight poster on continual confounding + our respective ConCon dataset on Thursday 17 Jul 4:30 pm - 7 pm PDT in East Exhibition Hall A-B: E-3309 icml.cc/virtual/2025... Please talk to them! :) Details below ⬇️
icml.cc
ICML Poster Where is the Truth? The Risk of Getting Confounded in a Continual WorldICML 2025
082
Reposted by Martin Mundt
Queer in AI @queerinai.com · 01/07/2025
🏳️‍🌈 Queer in AI is thrilled to announce another season of our affinity workshop at #NeurIPS2025! We announce a Call for Contributions to the workshop, with visa-friendly submissions due by 📅 July 31, 2025 (AOE), all other submissions due by 📅 August 14, 2025. #QueerInAI #CallForPapers
1104
Reposted by Martin Mundt
ACM FAccT @facct.bsky.social · 30/06/2025
We're happy to officially announce the location of #FAccT2026! Next year's conference will be held in Montreal, Canada 🇨🇦 Su Lin Blodgett and Zeerak Talat will be General Chairs, and Michael Madaio will be PC Chair 🎉 (thanks to MindView for the photo!)
Photo of the Town Hall meeting at last week's conference. The audience watches as Su Lin Blodgett announces the location of next year's conference. Su Lin Blodgett and Zeerak Talat will be General Chairs, and Michael Madaio will be PC Chair.
05716
Reposted by Martin Mundt
Dr Abeba Birhane @abeba.blacksky.app · 29/06/2025
dear computer vision people, labelling someone* an "activist" is not the disparage you think it is (*there is no claim in our paper that's not supported by empirical evidence so our work adheres to science by any standard. still...)
3637
Reposted by Martin Mundt
collasconf.bsky.social @collasconf.bsky.social · 28/06/2025
📢 Present your published work at #CoLLAs2025! Submit recent papers (JMLR, TMLR, NeurIPS, etc.) on lifelong/continual learning, LLMs, online learning & more. 🗓 Deadline: July 5 🔗 lifelong-ml.cc/Conferences/... #AI #MachineLearning #LifelongLearning #ContinualLearning
lifelong-ml.cc
CoLLAs
Collas
032
Martin Mundt @martinmundt.bsky.social · 06/06/2025
We are hiring a tenure-track prof in the computer science department at University of Bremen for the field of Computer Engineering with a focus on Distributed Systems Applications are still open until June 18th, so come join a fantastic set of colleagues! www.uni-bremen.de/en/universit...
uni-bremen.de
Job Vacancies - Universität Bremen
Offene Stellen
042
Reposted by Martin Mundt
ACM FAccT @facct.bsky.social · 01/06/2025
Are you based in Greece? 🇬🇷 Do you want to attend #FAccT2025 and have your entire registration fee waived? Volunteer for just 4 hours at the conference! Apply by June 3, 2025, at 11:59 pm anywhere on Earth: facctconference.org/2025/cfv2
163
Martin Mundt @martinmundt.bsky.social · 28/05/2025
We (+ @pranav-nlp.bsky.social) had tremendous fun presenting our cake-AI analogy to a really engaging audience. Thanks for the greatly thoughtful discussions 🙏 We are facing numerous socio-technical challenges in AI, but with talented fresh minds & increased awareness, there may be a bright future
060
Reposted by Martin Mundt
Pranav A @pranav-nlp.bsky.social · 27/05/2025
I am at the data story workshop hosted by @martinmundt.bsky.social where we talk about AI as cake! We redefine Yann LeCun's famous analogy beyond just learning types. From ingredients to selling - we break down how AI really works and who gets left out.
Martin presenting the intro slide of the talk
131
Martin Mundt @martinmundt.bsky.social · 23/05/2025
"Reasonable AI" got selected as a cluster of excellence www.tu-darmstadt.de/universitaet... Overwhelmingly happy to be part of RAI & continue working with the smart minds at TU Darmstadt & hessian.AI, while also seeing my new home at Uni Bremen achieve a historic success in the excellence strategy!
183
Martin Mundt @martinmundt.bsky.social · 14/05/2025
You may know batch-norm, but did you know it is a lightweight catalyst for open world learning? In "BOWL: A Deceptively Simple Open World Learner" we leverage BN stats to enable OoD detection & rapid active + continual learning! arxiv.org/abs/2402.04814 🚀 now accepted @collasconf.bsky.social
040
Reposted by Martin Mundt
Hanna Wallach @hannawallach.bsky.social · 03/05/2025
Exciting news!!! This just got into @icmlconf.bsky.social as a position paper!!! 🎉 More updates to come as we work on the camera-ready version!!!
04911
Martin Mundt @martinmundt.bsky.social · 08/05/2025
Horizontal, vertical, hybrid data partitioning: heterogeneity is tough to handle in federated learning! 🔥In “Scaling Probabilistic Circuits via Data Partitioning" - accepted at #UAI25 - we unify the different settings through aggregation of learned client distributions: arxiv.org/abs/2503.08141
074
Reposted by Martin Mundt
ContinualAI @continualai.bsky.social · 02/05/2025
Join us this Thursday 8 May for: U n l e a r n i n g ~ in continual scenarios ~ together with: Zhenyi Wang, Sijia Liu, and Kairan Zhao 6 PM CET / 9 AM PT / 12 PM ET Hope to see you there!!! Registration here: stanford.zoom.us/meeting/regi...
042
Martin Mundt @martinmundt.bsky.social · 02/05/2025
🔥Our work “Where is the Truth? The Risk of Getting Confounded in a Continual World" was accepted with a spotlight poster at ICML! arxiv.org/abs/2402.06434 -> we introduce continual confounding + the ConCon dataset, where confounders over time render continual knowledge accumulation insufficient ⬇️
2103
Reposted by Martin Mundt
Data Train @datatrain.bsky.social · 30/04/2025
Join us for a delicious Data Story by @martinmundt.bsky.social on the AI-cake analogy, hosted @dfki.bsky.social in Bremen! 👉 Info and registration: www.bremen-research.de/data-train/c... 👓 Read more about the research in Martin's thread below 🍰 Of course, there will be cake 😋
022
Martin Mundt @martinmundt.bsky.social · 30/04/2025
We are hosting a 3-hour interactive session on our Cake-AI analogy work (arxiv.org/abs/2502.03038) on May 27th @dfki.bsky.social Bremen. If you are around, please consider signing up to learn & discuss how the process of baking helps us understand design & socio-technical tensions of AI systems!⬇️
032
Martin Mundt @martinmundt.bsky.social · 07/04/2025
🚀We’ve created a spotlight program for early Postdoc/starting faculty/industry equivalent researchers to highlight their contributions & vision in a 30 minute spotlight talk at CoLLAs! It’s a unique opportunity & recognition! Applications are open until May 26 AOE: lifelong-ml.cc/Conferences/...
lifelong-ml.cc
CoLLAs
Collas
021
Martin Mundt @martinmundt.bsky.social · 02/04/2025
Gaming the system? … No paper in my ICML batch with negative ratings has posted rebuttals, in both tracks! I spend lots of time reviewing & give detailed comments. I see people complain about review quality constantly, but with such author behavior, what exactly do we expect?
030
Reposted by Martin Mundt
Pasquale Minervini @neuralnoise.com · 01/04/2025
Still ~8 days to apply for a postdoc position in multimodal foundation models at the University of Edinburgh! (@edinburgh-uni.bsky.social) -- Fully funded position until 2029 by the Generative AI Hub (@genaihub.bsky.social) to work with outstanding research teams! neuralnoise.com/2025/multimo...
084
Reposted by Martin Mundt
FX Coudert @nanoporous.net · 19/03/2025
French researcher, going to a conference in Houston, was forbidden entry to US; his work and personal electronics were both confiscated. Why? Because a “random search” of his cell phone revealed a negative personal opinion on Trump and the Trump administration. www.lemonde.fr/internationa...
lemonde.fr
Etats-Unis : un chercheur français refoulé pour avoir exprimé « une opinion personnelle sur la politique menée par l’administration Trump »
Le ministre de la recherche a dit sa « préoccupation », mercredi, après cette décision des autorités américaines. Le chercheur du CNRS aurait subi un contrôle aléatoire à son arrivée, avant que son or...
10220591300
Reposted by Martin Mundt
collasconf.bsky.social @collasconf.bsky.social · 07/03/2025
At #CoLLAs2025, we’re committed to fostering an inclusive and accessible research community: ✅ Reimbursable early registration & visa support ✅ Travel grants & fee waivers to reduce financial barriers ✅ Mentorship & visibility for early-career researchers Learn more: 🔗 lifelong-ml.cc/blogs/3
lifelong-ml.cc
CoLLAs
Collas
021
Martin Mundt @martinmundt.bsky.social · 06/03/2025
It’s striking how continual ML works seem to willingly place themselves in a box. It’s regularization or rehearsal or isolation, despite obvious complementarity w/ brain evidence. There’s no “one lifelong learning mechanism” & it’s honestly holding great ideas back unnecessarily
010
Reposted by Martin Mundt
Camila Gonzalez @camgonza.bsky.social · 04/03/2025
Join us for our March ContinualAI seminar on 𝐸𝑓𝑓𝑖𝑐𝑖𝑒𝑛𝑡 𝑓𝑖𝑛𝑒-𝑡𝑢𝑛𝑖𝑛𝑔 𝑡𝑒𝑐ℎ𝑛𝑖𝑞𝑢𝑒𝑠 (𝑎𝑑𝑎𝑝𝑡𝑒𝑟𝑠, 𝐿𝑜𝑅𝐴, 𝑎𝑛𝑑 𝑏𝑒𝑦𝑜𝑛𝑑) with Eric Coleman and Wentao Zhang! ♾️ Thursday, March 6th 🕘 9 AM PST | 🕛 12 PM EST | 🕕 6 PM CET Register here 👉 stanford.zoom.us/meeting/regi...
021
Martin Mundt @martinmundt.bsky.social · 04/03/2025
As a reviewer for various ML confs right now, I feel like this needs to be said again: An introduction is not good if it’s so generic that it can be copy-pasted into any other paper on the same topic. The intro motivates me to read the paper carefully - please don’t waste it.
100
Reposted by Martin Mundt
collasconf.bsky.social @collasconf.bsky.social · 25/02/2025
⏳ One Day Left! ⏳ The #CoLLAs2025 abstract deadline is tomorrow! 📅 Still on the fence? Checkout the exciting lineup of invited speakers. This is your chance to share your work and connect with top researchers in the field! Submit your abstract today! 📝 🔗 lifelong-ml.cc
031
Martin Mundt @martinmundt.bsky.social · 24/02/2025
If you are attending #AAAI25 make sure to take part in our 3rd Continual Causality Bridge, tomorrow Feb 25th. I can’t travel myself due to family medical reasons 😢, but we have an exciting program with amazing speakers on #continuallearning & #causality: www.continualcausality.org/program/
030
Reposted by Martin Mundt
collasconf.bsky.social @collasconf.bsky.social · 20/02/2025
📢 Deadline Extension Alert! 📢 Good news! We’re extending the #CoLLAs2025 submission deadlines: 📝 Abstracts: Feb 26, 2025, 23:59 AoE 📄 Papers: Mar 3, 2025, 23:59 AoE More time to refine your work—don't miss this chance to contribute to #lifelong-learning research! 🚀 🔗 lifelong-ml.cc
lifelong-ml.cc
CoLLAs
Collas
034
Reposted by Martin Mundt
Martin Trapp @trappmartin.eurosky.social · 20/02/2025
Are interested in making #computervision models more #reliable and #robust by accounting for #uncertainties? Then consider submitting your awesome work to our @cvprconference.bsky.social workshop! uncertainty-cv.github.io/2025/
uncertainty-cv.github.io
UNCV Workshop @ CVPR 2025
CVPR 2025 Workshop on Uncertainty Quantification for Computer Vision.
0104
Reposted by Martin Mundt
Crystal Rogers, PhD @rogerslabucd.bsky.social · 19/02/2025
Pretty sad. Just got the email that CZI is canceling the second round of Diversity Leadership Awards. Private industry will definitely not fill the hole that NIH and NSF are leaving. 😢💔
Thank you for submitting your Letter of Intent (LOI) to CZI. We appreciate your interest in our work.

CZI has decided not to continue with the second round of its Science Diversity Leadership Awards. We are committed to supporting groundbreaking research that advances the frontiers of scientific knowledge in pursuit of our mission to cure, prevent, or manage all diseases by the end of the century. We will provide information on future funding opportunities.

We look forward to staying in touch.

Bil Clemons, Program Officer, CZI
52717279
Martin Mundt @martinmundt.bsky.social · 18/02/2025
Why has continual ML not had its breakthrough yet? In our new collaborative paper w/ many amazing authors, we argue that “Continual Learning Should Move Beyond Incremental Classification”! We highlight 5 examples to show where CL algos can fail & pinpoint 3 key challenges arxiv.org/abs/2502.11927
0103
Martin Mundt @martinmundt.bsky.social · 06/02/2025
🍰Super proud of our newest work: “The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation” - arxiv.org/abs/2502.03038 🍰We extend Yann LeCun’s AI cake analogy to relate socio-technical outcomes to the AI life-cycle! More details below ⬇️ 1/4
1174
Reposted by Martin Mundt
Queer in AI @queerinai.com · 03/02/2025
Our workshop has been extended till Feb 20. We are looking forward for your papers at NAACL's Queer in AI workshop.
01717