Andreas Krause

SDPO enables RL agents to learn from rich feedback (i.e., not only whether an attempt failed, but why it failed, such as error messages). Even without such rich feedback, SDPO can reflect on past attempts and outperform GRPO. SDPO also accelerates solution discovery at test time!

Excited to be back at AI House Davos! Looking forward to connecting and engaging in inspiring discussions, panels and roundtables about trustworthy AI, AI infrastructure and much more!

@eth-ai-center.bsky.social @ethz.ch @csateth.bsky.social

ICML reaffirms its support to the community and standards of conduct:
- We do not tolerate harassment or other improper conduct;
- Academic integrity is paramount;
- We redouble our support to peer review, with more incentives for reviewers & financial support for OpenReview

icml.cc/public/blog#...

Excited to attend @euripsconf.bsky.social and the @ellis.eu UnConference in Copenhagen this week!

On my way to Montreal for COLM. Let me know if you’re also coming! I’d be very happy to catch up!

We present our poster at #1013 in the Wednesday morning session.

Joint work with the amazing Ryo Bertolissi, @idoh.bsky.social, @arkrause.bsky.social.

Here's the detailed technical report with many more details: github.com/swiss-ai/ape...

Apertus: a fully open, transparent, multilingual language model EPFL, ETH Zurich and the Swiss National Supercomputing Centre (CSCS) released Apertus today, Switzerland’s first large-scale, open, multilingual language model — a milestone in generative AI for trans...

EPFL, ETH Zurich, and CSCS today released Apertus, Switzerland's first large-scale, multilingual language model (LLM). As a fully open LLM, it serves as a building block for developers and organizations to create their own applications.
ethz.ch/en/news-and-...

Clinical notes are messy, inconsistent, and unstructured—yet they hold some of the most valuable signals in real-world clinical practice.

Join us today at ICML at the Foundation Models for Structured Data workshop to see how we can make sense of these notes!
📍 West Ballroom D

In our ICML paper, we study fine-tuning a generalist policy for multiple tasks. We ask, provided a pre-trained policy, how can we maximize multi-task performance with a minimal number of additional demonstrations?

📌 We are presenting a possible solution on Wed, 11am to 1.30pm at B2-B3 W-609!

ETH Zürich students gain AI skills using the “Alps” supercomputer: www.cscs.ch/science/comp... #students #AI #supercomputer #wearealps

✨ Very excited to share that our work "Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs" will be presented at ICLR! ✨

🗓️ Wednesday, April 23rd, 7:00–9:30 p.m. PDT
📍 Hall 3 + Hall 2B #257

Joint work with my fantastic collaborators Sascha Bongni,
@idoh.bsky.social, @arkrause.bsky.social

What is the place of exploration in today's AI landscape and in which settings can exploration algorithms address current open challenges?

Join us to discuss this at our exciting workshop at @icmlconf.bsky.social 2025: EXAIT!

exait-workshop.github.io

#ICML2025

We've released our lecture notes for the course Probabilistic AI at ETH Zurich, covering uncertainty in ML and its importance for sequential decision making. Thanks a lot to @jonhue.bsky.social for his amazing effort and to everyone who contributed! We hope this resource is useful to you!

Schematic illustration of a scalar-valued residual deep GP with L hidden layers. The last layer is a scalar-valued GP on the manifold. If it is not present, the model is manifold-valued. If it is replaced with a Gaussian vector field (GVF), the model is a vector field on the manifold.

Excited to share our ICLR 2025 oral "Residual Deep Gaussian Processes on Manifolds"!

With @vabor112.bsky.social & @arkrause.bsky.social, we introduce manifold-to-manifold GPs that can be composed together, generalising deep GPs to manifolds. Applications include wind prediction & Bayes opt! 1/n

Reflecting back on an inspiring week at www.aihousedavos.com — such a vibrant environment to discuss, with AI thought leaders across academia, industry and the public sector, challenges around safe and responsible AI, and harnessing AI for sustainable development!

🚨 New reinforcement learning algorithms 🚨

Excited to announce MaxInfoRL, a class of model-free RL algorithms that solves complex continuous control tasks (including vision-based!) by steering exploration towards informative transitions.

Details in the thread 👇

We’re presenting our work “When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL” today at NeurIPS. Come join us in West at poster #6604 from 16:30-19:30!

Joint work with my fantastic collaborators Bhavya Sukhija, Yarden As, Florian Dörfler, @arkrause.bsky.social

Tomorrow I’ll be presenting our recent work on improving LLMs via local transductive learning in the FITML workshop at NeurIPS.
Join us for our ✨oral✨ at 10:30am in east exhibition hall A.

Joint work with my fantastic collaborators Sascha Bongni, @idoh.bsky.social, @arkrause.bsky.social

We’re presenting our work “Transductive Active Learning: Theory and Applications” now at NeurIPS. Come join us in East at poster #4924!

Joint work with my fantastic collaborators Bhavya Sukhija, Lenart Treven, Yarden As, @arkrause.bsky.social

Looking forward to attending!

Assistant Professor (Tenure Track) of Computer Science – Responsible Artificial Intelligence

📣 We have a tenure-track faculty opening in Responsible AI at @ethzurich.bsky.social :
ethz.ch/en/the-eth-z.... Deadline Nov 30 for full consideration. ETH Zurich is a vibrant environment for AI research with the ETH AI Center etc. Please help spread the word!

📣 Last call for the Ph.D. and Postdoc Fellowships at the ETH AI Center -- Deadline Nov 19 '24 t.co/aYI5tWXUWK @ethzurich.bsky.social

Happy to join this platform and talk about ML & AI research (of the blue sky nature and otherwise...)