Patrik Reizinger's Avatar

Patrik Reizinger

@rpatrik96.bsky.social

PhD student working on understanding why neural nets generalize @MPI Tรผbingen | ex-Vector | path2phd.substack.com | ๐Ÿ‡ญ๐Ÿ‡บ ๐Ÿ‡ช๐Ÿ‡บ

270 Followers  |  108 Following  |  4 Posts  |  Joined: 21.11.2024  |  1.5811

Latest posts by rpatrik96.bsky.social on Bluesky

Preview
The path to PhD - Advice from a young scientist I am Scientist ยท Episode

I had the pleasure of being interviewed on the @i-am-scientist.bsky.social podcast by @lisaschmors.bsky.social and @philipphubert.bsky.social . I talk about how I ended up writing my newsletter (path2phd.substack.com) and the people who supported me all along. Enjoy!

02.05.2025 17:12 โ€” ๐Ÿ‘ 4    ๐Ÿ” 1    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 1
Post image

Soโ€”does this mean theory is doomed, and AI engineering is just a random walk? Not at all!

๐Ÿ’ก @rpatrik96.bsky.social @wielandbrendel.bsky.social Randall Balestriero did an amazing job clarifying where theory can help practiceโ€”and where practice should inspire theory.

๐Ÿค

18.04.2025 14:15 โ€” ๐Ÿ‘ 1    ๐Ÿ” 1    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 0

Kudos to the great team @ninamiolane.bsky.social @rpatrik96.bsky.social @charlesoneill.bsky.social Harald Maurer ๐Ÿ™

04.03.2025 19:43 โ€” ๐Ÿ‘ 6    ๐Ÿ” 3    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

How can neural nets extract *interpretable* features from dataโ€”& uncover new science?

๐Ÿ‘‰ Discover our mathematical framework tackling this question w/ identifiability theory, compressed sensing, interpretability & geometry!๐ŸŒ

By @david-klindt.bsky.social @rpatrik96.bsky.social C. O'Neill H Maurer

05.03.2025 14:41 โ€” ๐Ÿ‘ 18    ๐Ÿ” 8    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 1

New preprint!๐Ÿš€

Decoding neural representations is a challenge in neuroscience & AI.

๐Ÿ‘‰ Learn how identifiability theory, compressed sensing & interpretability research -w/ a dash of geometry- can help!

@david-klindt.bsky.social @rpatrik96.bsky.social C. O'Neill H. Maurer @ninamiolane.bsky.social

05.03.2025 14:43 โ€” ๐Ÿ‘ 8    ๐Ÿ” 4    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Hiring announcement: ELLIS Institute Tรผbingen is looking for ML Researchers & Engineers for Open-Source AI Tutoring (m/f/d). The image features a white background with bold black text and the colorful ELLIS logo at the bottom.

Hiring announcement: ELLIS Institute Tรผbingen is looking for ML Researchers & Engineers for Open-Source AI Tutoring (m/f/d). The image features a white background with bold black text and the colorful ELLIS logo at the bottom.

๐Ÿš€ Weโ€™re hiring! Join Bernhard Schรถlkopf & me at @ellisinsttue.bsky.social to push the frontier of #AI in education!

Weโ€™re building cutting-edge, open-source AI tutoring models for high-quality, adaptive learning for all pupils with support from the Hector Foundation.

๐Ÿ‘‰ forms.gle/sxvXbJhZSccr...

11.02.2025 16:34 โ€” ๐Ÿ‘ 8    ๐Ÿ” 14    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 1
NeurIPS Poster Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD PromptsNeurIPS 2024

Check out our @neuripsconf.bsky.social spotlight on showing how language models learn to extrapolate and compose language rules.

See you on Fri 13 Dec 4:30 p.m. PST โ€” 7:30 p.m. PST at poster #2702 in East Hall.

neurips.cc/virtual/2024...

13.12.2024 16:59 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
ELLIS PhD Award 2024 in text and three photos of the winners, then the ELLIS logo at the bottom

ELLIS PhD Award 2024 in text and three photos of the winners, then the ELLIS logo at the bottom

Congrats to the recipients of the 2024 ELLIS PhD Award!

Co-winners: @koloskova.bsky.social (efficiency in decentralized learning) & Luigi Gresele (identifiable representation learning)
Runner up: @schwarzjn.bsky.social (sparse parameterizations)

Read more about them: bit.ly/4fg4jkg
#AI #ML

12.12.2024 08:46 โ€” ๐Ÿ‘ 42    ๐Ÿ” 5    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 2
Post image

1/ Hi all, I am at #NeurIPS2024 and I will be hiring a postdoc in probabilistic machine learning starting asap.

Research interests: amortized, approximate & simulator-based inference, Bayesian optimization, and AI4science.

Get in touch for a chat or come to our posters today 11AM or Friday 11AM!

11.12.2024 16:26 โ€” ๐Ÿ‘ 25    ๐Ÿ” 11    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 1
Preview
How to Merge Your Multimodal Models Over Time? Model merging combines multiple expert models - finetuned from a base foundation model on diverse tasks and domains - into a single, more capable model. However, most existing model merging approaches...

๐Ÿ“„ New Paper: "How to Merge Your Multimodal Models Over Time?"

arxiv.org/abs/2412.06712

Model merging assumes all finetuned models are available at once. But what if they need to be created over time?

We study Temporal Model Merging through the TIME framework to find out!

๐Ÿงต

11.12.2024 18:00 โ€” ๐Ÿ‘ 24    ๐Ÿ” 7    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 2
Research Assistant/Associate in Machine Learning (Fixed Term) - Job Opportunities - University of Cambridge Research Assistant/Associate in Machine Learning (Fixed Term) in the Department of Engineering at the University of Cambridge.

We are looking for a PostDoc on human-AI interaction to work with @mirizilka.bsky.social

The project studies systems used in law enforcement or legal decision-making, when humans act on recommendations/predictions made by ML algorithms.

Email for details.

www.jobs.cam.ac.uk/job/49538/

11.12.2024 20:16 โ€” ๐Ÿ‘ 7    ๐Ÿ” 2    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 1

Check out our
@neuripsconf.bsky.social
spotlight on showing a useful inductive bias in language models to extrapolate language rules.

See you on Fri 13 Dec 4:30 p.m. PST โ€” 7:30 p.m. PST at poster #2702.

06.12.2024 18:47 โ€” ๐Ÿ‘ 3    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

Next week I will be in Berkeley. Reach out if you'd like to talk about OOD/compositional generalization, causality, SSL, or inductive biases.

28.11.2024 07:26 โ€” ๐Ÿ‘ 1    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

The โœจML Internship Feedโœจ is here!

@serge.belongie.com and I created this feed to compile internship opportunities in AI, ML, CV, NLP, and related areas.

The feed is rule-based. Please help us improve the rules by sharing feedback ๐Ÿงก

๐Ÿ”— Link to the feed: bsky.app/profile/did:...

22.11.2024 21:46 โ€” ๐Ÿ‘ 63    ๐Ÿ” 16    ๐Ÿ’ฌ 7    ๐Ÿ“Œ 1
Poster of the EIPOD call

Poster of the EIPOD call

Join the Interdisciplinary Postdoc Fellowship Program at the European Molecular Biology Laboratory (EMBL), one of the best places to do research in modern biology and develop your career.

Great opportunities for statisticians, comp. biologists, AI experts, mathem. modelers!
www.embl.org/eipod-linc

22.11.2024 09:02 โ€” ๐Ÿ‘ 41    ๐Ÿ” 32    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

@rpatrik96 is following 20 prominent accounts