Training LLMs with verifiable rewards uses 1bit signal per generated response. This hides why the model failed. Today, we introduce a simple algorithm that enables the model to learn from any rich feedback! And then turns it into dense supervision. (1/n)

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.

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!

✨ 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

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!

I'm very excited to share notes on Probabilistic AI that I have been writing with @arkrause.bsky.social 🥳 arxiv.org/pdf/2502.05244 These notes aim to give a graduate-level introduction to probabilistic ML + sequential decision-making. I'm super glad to be able to share them with all of you now!

Overfitting, as it is colloquially described in data science and machine learning, doesn’t exist. www.argmin.net/p/thou-shalt...

The slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now 🥳 They cover quite a bit from basic information theory to some recent papers: blackhc.github.io/balitu/ and I'll try to add proper course notes over time 🤗

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

Assume that the nodes of a social network can choose between two alternative technologies: B and X. A node using B receives a benefit with respect to X, but there is a benefit to using the same tech as the majority of your neighbors. Assume everyone uses X at time t=0. Will they switch to B?