David Rügamer
@davidruegamer.bsky.social
570 followers 270 following 48 posts
Associate Prof @ LMU Munich PI @ Munich Center for Machine Learning Ellis Member Associate Fellow @ relAI ----- https://davidruegamer.github.io/ | https://www.muniq.ai/ ----- BNNs, UQ in DL, DL Theory (Overparam, Implicit Bias, Optim), Sparsity
Posts Media Videos Starter Packs
Reposted by David Rügamer
munichcenterml.bsky.social
𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗳𝘂𝗹𝗹𝘆 𝗳𝘂𝗻𝗱𝗲𝗱 𝗣𝗵𝗗 𝗣𝗼𝘀𝗶𝘁𝗶𝗼𝗻𝘀: We are offering several PhD positions across our various research areas, open to highly qualified candidates.
‼️ The application portal will be open from 15 October to 14 November 2025.

Find out more: mcml.ai/opportunitie...
davidruegamer.bsky.social
Works like a charm for structured sparsity too 🔥 Tested on a variety of architectures: sparse attention heads, sparse inputs, sparse conv filters, sparse NODEs,... And no setup changes needed, just a regularized gating variable! Spotlight @NeurIPS + Oral @EurIPS 🤩
Preprint: arxiv.org/abs/2509.23898
davidruegamer.bsky.social
Any updates on the Salon des Refusés? Do you also accept position papers?
davidruegamer.bsky.social
🚀 RTG-METEOR is hiring!

Apply now for Doctoral (4y) or Postdoc (3y) positions (TV-L E13, 100%) at LMU & TUM.
Research focus: bridging Machine Learning & Control Theory for complex dynamical systems.

📅 Deadline: Nov 13, 2025
📍 Start: Apr 1, 2026

www.portal.graduatecenter.lmu.de/ocgc/meteor
Application for RTG METEOR Doctoral and Postdoctoral Positions | Application Portal of the GraduateCenter
www.portal.graduatecenter.lmu.de
Reposted by David Rügamer
kdau.bsky.social
The Journal-to-Conference track is back at AISTATS🌴!

The track invites authors of papers published or accepted after January 1st, 2024 in AoS, Biometrika, JASA, JMLR and JRSS B to present their work as posters at #AISTATS2026 in Tangier, Morocco (May 2nd-5th 2026).

📅 Deadline: 31 January 2026
davidruegamer.bsky.social
I am not sure if they are opposed to this, but "[t]he Mexico City location will host approximately five hundred attendees". Definitely seems too small, given that China alone had almost 1,600 papers last year: papercopilot.com/paper-list/n... (click on Aff. Country)
NeurIPS 2024 Accepted Paper List - Paper Copilot
papercopilot.com
davidruegamer.bsky.social
@zeynepakata.bsky.social Maybe suggest that they accept EurIPS Copenhagen as an official third location. I think many PhD students would be happy to "just" present in Europe :)
davidruegamer.bsky.social
Right. Maybe ICLR should be more precise in their statement then (e.g., it currently only refers to 'hidden' injections).
davidruegamer.bsky.social
Or would I still be accused of collusion, since I am technically influencing the review---even though what I am really doing is making public that I just want to be treated fairly?
davidruegamer.bsky.social
I was wondering: What if the prompt is not hidden and I simply want to protect myself from lazy reviewers? For instance, I could openly include a protection sentence in the appendix that instructs an LLM to add a subtle identifier, allowing authors and chairs to detect LLM-generated reviews.
davidruegamer.bsky.social
This is for ICLR 2025. While I see the "Theory" effect Ahmad described, I am not sure we can draw any conclusions from the small sample size of an AC batch. My batch includes one paper with an average of 4, one with 3.6, and the rest are below 3.5 (so perhaps more in line with Ahmad's findings).
Reposted by David Rügamer
auai.org
uai2025 @auai.org · Jul 22
presentations from the oral session #1 on learning

www.auai.org/uai2025/sche...
davidruegamer.bsky.social
That's awesome @serge.belongie.com !!

Quick question: How should authors present at both NeurIPS and EurIPS if the conferences have overlapping dates?
davidruegamer.bsky.social
Can transformers learn full Bayesian inference in context? 🤔

👉 Come find out and visit our poster E-1205 in the East Hall this morning at #ICML2025 presented by @arikreuter.bsky.social

icml.cc/virtual/2025...
ICML Poster Can Transformers Learn Full Bayesian Inference in Context?ICML 2025
icml.cc
Reposted by David Rügamer
rickmer.bsky.social
Looking forward to presenting our paper "Adjustment for Confounding using Pre-Trained Representations" at #ICML2025 in Vancouver next week! 🎉🇨🇦

Feel free to check out our paper and reach out if you're attending or would like to discuss!

📄 Paper: arxiv.org/abs/2506.14329
davidruegamer.bsky.social
Two open postdoctoral positions in applied AI from my heritage science colleagues next door:

> Postdoctoral Researchers in AI and Machine Learning Applications in Heritage Science and Archaeology

1) job-portal.lmu.de/jobposting/d...

2) job-portal.lmu.de/jobposting/1...
davidruegamer.bsky.social
If it's not too much effort, I'd be curious to see what specific work you're referring to 🤓
Reposted by David Rügamer
rickmer.bsky.social
It has been a great honour to presented our paper "Additive Model Boosting: New Insights and Path(ologie)s" at #AISTATS 2025!🚀 Joint work with @davidruegamer.bsky.social!

Check out the paper and feel free to reach out:
🔗 arxiv.org/abs/2503.05538
davidruegamer.bsky.social
Open AI for science PhD/Postdoc position at the Institute for Assyriology and Hittitology in collaboration with muniq.ai and the machine learning consulting unit of the MCML ( @munichcenterml.bsky.social ). Deadline: May 19

job-portal.lmu.de/jobposting/e...
PhD or Postdoctoral Researcher in AI for Science / Machine Learning at the ERC Project: “Rewriting the End of Cuneiform Civilization” (m/f/x)
job-portal.lmu.de
davidruegamer.bsky.social
#3: Adjustment for Confounding using Pre-Trained Representations with @rickmer.bsky.social @tnagler.bsky.social
davidruegamer.bsky.social
#2: Revisiting Unbiased Implicit Variational Inference with
Tobi Pielok @slds-lmu.bsky.social