iiinova — where your digital self keeps evolving

Yuli Slavutsky @yulislavutsky.bsky.social · 03/12/2025

Uncertainty estimation fails under distribution shifts. Why? Partly because in stats, even Bayesian stats, we treat x as given. But intuitively data makes different models plausible. For reliable uncertainty, we need to account for it explicitly. Come chat with me about it tomorrow at my poster

neurips.cc

NeurIPS Poster Quantifying Uncertainty in the Presence of Distribution ShiftsNeurIPS 2025

161

Reposted by Yuli Slavutsky

Nicolas Beltran-Velez @velezbeltran.bsky.social · 12/12/2024

Hello! We will be presenting Estimating the Hallucination Rate of Generative AI at NeurIPS. Come if you'd like to chat about epistemic uncertainty for In-Context Learning, or uncertainty more generally. :) Location: East Exhibit Hall A-C #2703 Time: Friday @ 4:30 Paper: arxiv.org/abs/2406.07457

0234

Reposted by Yuli Slavutsky

claudia shi @claudiashi.bsky.social · 10/12/2024

The circuit hypothesis proposes that LLM capabilities emerge from small subnetworks within the model. But how can we actually test this? 🤔 joint work with @velezbeltran.bsky.social @maggiemakar.bsky.social @anndvision.bsky.social @bleilab.bsky.social Adria @far.ai Achille and Caro

2156

Yuli Slavutsky @yulislavutsky.bsky.social · 10/12/2024

Fri 13 Dec 11 a.m. PST — 2 p.m. PST East Exhibit Hall A-C #2204

020

Yuli Slavutsky @yulislavutsky.bsky.social · 10/12/2024

In this paper, we tackle shifts caused by an unknown attribute with an approach opposite to bootstrapping: we use small samples to generate synthetic environments with different "kinds" of classes and learn more robust data representations.

120

Yuli Slavutsky @yulislavutsky.bsky.social · 10/12/2024

But in zero-shot, we face new classes at test time. To adapt, we need to know which "kind" of classes to emphasize. But in reality, the shift is often unknown.

120

Yuli Slavutsky @yulislavutsky.bsky.social · 10/12/2024

Class distribution shifts are often seen as the easiest to handle—that's often true for supervised learning, thanks to reweighting/resampling.

120

Yuli Slavutsky @yulislavutsky.bsky.social · 10/12/2024

I'm on my way to #NeurIPS2024. On Friday I'm going to present my latest paper with Yuval Benjamini. The gist is in the comments, and come chat with me to hear more!

174

Reposted by Yuli Slavutsky

Nicolas Beltran-Velez @velezbeltran.bsky.social · 02/12/2024

I am very excited to share our new Neurips 2024 paper + package, Treeffuser! 🌳 We combine gradient-boosted trees with diffusion models for fast, flexible probabilistic predictions and well-calibrated uncertainty. paper: arxiv.org/abs/2406.07658 repo: github.com/blei-lab/tre... 🧵(1/8)