@jonhue.bsky.social
PhD student at ETH Zurich jonhue.github.io
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.
Paper: arxiv.org/pdf/2410.05026
Joint work with the amazing @marbaga.bsky.social, @gmartius.bsky.social, @arkrause.bsky.social
We propose an algorithm that does this by actively maximizing expected information gain of the demonstrations, with a couple of tricks to estimate this quantity and mitigate forgetting.
Interestingly, this solution is viable even without any information about pre-training!
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!
Our method significantly improves accuracy (measured as perplexity) for large language models and achieves a new state-of-the-art on the Pile benchmark.
If you're interested in test-time training or active learning, come chat with me at our poster session!
We introduce SIFT, a novel data selection algorithm for test-time training of language models. Unlike traditional nearest neighbor methods, SIFT uses uncertainty estimates to select maximally informative data, balancing relevance & diversity.
21.04.2025 14:40 — 👍 2 🔁 0 💬 1 📌 0Paper: arxiv.org/pdf/2410.08020
21.04.2025 14:38 — 👍 0 🔁 0 💬 1 📌 0
✨ 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!
17.02.2025 07:19 — 👍 58 🔁 10 💬 1 📌 0Unfortunately not as of now. We may also release Jupyter notebooks in the future, but this may take some time.
12.02.2025 22:25 — 👍 0 🔁 0 💬 1 📌 0I'm glad you find this resource useful Maximilian!
11.02.2025 15:26 — 👍 1 🔁 0 💬 0 📌 0Noted. Thanks for the suggestion!
11.02.2025 09:01 — 👍 1 🔁 0 💬 0 📌 0Very glad to hear that they’ve been useful to you! :)
11.02.2025 08:37 — 👍 2 🔁 0 💬 1 📌 0
table of contents:
11.02.2025 08:35 — 👍 4 🔁 0 💬 1 📌 0Huge thanks to the countless people that helped in the process of bringing this resource together!
11.02.2025 08:20 — 👍 2 🔁 0 💬 1 📌 0
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...
30.01.2025 15:35 — 👍 70 🔁 12 💬 11 📌 5
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 🤗
Preprint: arxiv.org/pdf/2410.08020
13.12.2024 18:33 — 👍 2 🔁 0 💬 1 📌 0Tomorrow 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
Paper: arxiv.org/pdf/2402.158...
Virtual poster: neurips.cc/virtual/2024...
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
Spread of innovation in a small world network.
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?
