
Claire Vernade @claireve.bsky.app
@vernadec
Followers
4K
Following
8K
Media
92
Statuses
1K
now on BlueSky @claireve. I tweet on Machine Learning, mostly Bandits, RL and Learning Theory. Group Leader in Tübingen @ml4science.
Tübingen, Deutschland
Joined November 2015
I’ve moved to the butterfly place 🦋 and I suspect I won’t be back here much because it’s so much nicer there. Find me at the handle claireve over there. Ciao Elon 👋, whom I do not follow and yet continues to pollute my thread every day
3
1
34
I and a few others are lending our time to the community to chat to anyone around the world with an internet connection! Book a slot if you want to chat. I've talked to folks about how to get involved in research, which grad program to choose, and much more!
Wanna chat with an experienced learning theory researcher? We have open office hours online with four awesome folks, Surbhi Goel (@SurbhiGoel_), Gautam Kamath (@thegautamkamath), Ayush Sekhari (@ayush_sekhari), Lydia Zakynthinou (@zakynthinou)! Book a slot and ask them anything!
1
4
28
🚨 Submissions for ALT2026 are now open! Submit your best work and join us in Toronto!🚨 Deadline: October 2 AoE Conference: Feb 23-26, 2026 https://t.co/PqRSa6xRMz
algorithmiclearningtheory.org
The 37th International Conference on Algorithmic Learning Theory
0
12
20
Dear Reviewers, It is completely fine to admit you were wrong in your initial evaluations. You will not lose anything, and the authors, your AC, and your SAC will appreciate your intellectual honesty. Best, One of the SACs
2
16
174
Giving two talks tomorrow at @RL_Conference on Imitation Learning and IRL in multi-agent systems See you at 11am at @RLBRew_RLC and at 4pm at the Causal Reinforcement Learning workshop! I'll also present our recent work on combining Behavioral Cloning and PbRL at @RLBRew_RLC
2
4
48
tl;dr - IPAM, the Institute of Pure and Applied Mathematics at UCLA, will shut down in a few months if their NSF funding isn't restored or replaced. The birthplace of compressed sensing, as well as lots of advances in ML and AI later picked up by industry.
Terence Tao has written a thread on Mathstodon about the damage being caused by the grant freezes at UCLA. https://t.co/6yJzG42Jxb
21
108
806
last year's edition was so much fun I'm really looking forward to this one!! join us in San Diego :))
Delighted to announce that the 2nd edition of our workshop has been accepted to #NeurIPS2025! We have an amazing lineup of speakers: @WenSun1, @ajwagenmaker, @yayitsamyzhang, @MengdiWang10, @nanjiang_cs, Alessandro Lazaric, and a special guest!
2
6
26
📢 About 2 weeks to go until #CoLLAs2025! Here’s what you need to make the most of it. 🗓 Program: https://t.co/TbD7mFNnox ✅ Accepted Papers: https://t.co/JKaF8fUiLX 📍 Venue & Local Info: https://t.co/IG7sJOan9N 🔗 Registration & conference details:
0
9
17
I’m gonna be recruiting students thru both @LTIatCMU (NLP) and @CMU_EPP (Engineering and Public Policy) for fall 2026! If you are interested in reasoning, memorization, AI for science & discovery and of course privacy, u can catch me at ACL! Prospective students fill this form:
📣Thrilled to announce I’ll join Carnegie Mellon University (@CMU_EPP & @LTIatCMU) as an Assistant Professor starting Fall 2026! Until then, I’ll be a Research Scientist at @AIatMeta FAIR in SF, working with @kamalikac’s amazing team on privacy, security, and reasoning in LLMs!
5
50
284
Everyone's talking about AI performance on the IMO. Let me highlight 🇨🇦Canadian 11th grader Warren Bei🇨🇦, one of five participants with a *perfect* 42/42. This is his *fifth* (and final) IMO representing Canada, with three golds and two silvers. (➡️ MIT undergrad in the fall)
22
78
2K
I wrote a short post on some etiquette for a seemingly mundane task: declining an offer (for a job, internship, grad school, etc). Link in next tweet. 1/2
4
9
144
ICLR 2025 test of time award goes to Adam, and the runner-up to @DBahdanau(-@kchonyc-@Yoshua_Bengio) Attention Notes: - Second ICLR ToT in a row for @dpkingma (last year: VAEs) - Both awards this year feature folks at Canadian schools - Runners up last year and this ft NYU folks
Announcing the Test of Time awards for ICLR 2025! This award recognizes papers published ten years ago at ICLR 2015 that have had a lasting impact on the field. Congratulations to the authors! https://t.co/Z8WEYSEFY7
2
9
135
EWRL is happening in Tübingen this year! Checkout our 🦋 posts. When? September 17-19, 2025. https://t.co/I73FwkO9WM
0
4
6
So collusion rings are still a thing at top conferences. @openreviewnet has all the data across all top tier ml conferences — what are they currently do to solve this. What top tier conf is willing to release data of bidding patterns so we can analyze the problem at scale.
18
19
291
I have the honour to chair the tutorial call with Claire Monteleoni this year and we are looking forward to the great proposals you’ll send to us.
ICML 2025 is calling for Tutorials! Perfect chance to show off that latest breakthrough you can’t stop talking about. If you can teach it without tears or meltdown, you can definitely give a tutorial!
0
2
17
Dynamic programming alternatives to dynamic programming for optimal control. Replace your Bellman equation with backpropagation.
argmin.net
Avoiding dynamic programming with dynamic programming
5
12
108
A very exciting personal update: In January, I’ll be joining @CMUMLD as tenure-track assistant professor! My lab will focus on the mathematical foundations of, and new algorithms, for decision making. This includes everything from reinforcement learning in the physical world
26
44
409
In case that wasn't explicit enough: I'll be posting more there, and increasingly less here. The combination of the new AI/data sharing policy and noticeable decrease in quality and experience since Twitter was bought have finally proven to be too much.
4
7
68
All you want to know about spectral transformers in one webpage, papers & code: (& we'll try to keep it updated!) https://t.co/a0ey8ADfK9
sites.google.com
Abstract Can we build neural architectures that go beyond Transformers by leveraging principles from dynamical systems? We introduce a novel approach to sequence modeling that draws inspiration from...
1
44
244
I have made a few starter packs for those looking for people on the other site. Differential privacy: https://t.co/dcjub2m2bc Waterloo CS faculty: https://t.co/2PK1I9mZoN NYU CS faculty: https://t.co/c3Mtx6AbNs Let me know if you belong to any of these groups and I missed you!
3
8
82
📢 Post-Bayesian online seminar series coming!📢 To stay posted, sign up at https://t.co/Tx3ecXKdC8 We'll discuss cutting-edge methods for posteriors that no longer rely on Bayes Theorem. (e.g., PAC-Bayes, generalised Bayes, Martingale posteriors, ...) Pls circulate widely!
docs.google.com
Information to be added to the post-Bayes mailing list.
2
41
189