iiinova — where your digital self keeps evolving

Sebastian Bordt @sbordt.bsky.social · 16/06/2026

How do you know if your training recipe is ready to be scaled up? Measure effective and propagating updates. Read about these tools in our latest blog post! sbordt.substack.com/p/how-to-mea...

000

Sebastian Bordt @sbordt.bsky.social · 18/04/2026

Over at 3quarksdaily, there are two thought provoking pieces by Dwight Furrow about the AI-consciousness debate: 3quarksdaily.com/3quarksdaily... 3quarksdaily.com/3quarksdaily...

3quarksdaily.com

3 Quarks Daily - Science Arts Philosophy Politics Literature

Science Arts Philosophy Politics Literature

000

Reposted by Sebastian Bordt

Naomi Saphra @nsaphra.bsky.social · 02/04/2026

ah, a new possible addition to the canon of SIGBOVIK AI papers

2487

Sebastian Bordt @sbordt.bsky.social · 03/12/2025

Our spotlight paper is happening today at the #NeurIPS poster session! Drop by if you want to chat about the nitty-gritty details of large-scale transformer training!

010

Sebastian Bordt @sbordt.bsky.social · 01/12/2025

Ever wondered about the rationale behind transformer training details like qk-norm, learning rate, and z-loss? Read this blog post to find out more!

open.substack.com

Why Can We Train Large Models with Large Learning Rates?

Infinite-width theory may explain the training dynamics of finite-width neural networks after all.

020

Reposted by Sebastian Bordt

Ulrike Luxburg @ulrikeluxburg.bsky.social · 07/11/2025

Here is a formal impossibility result for XAI: Informative Post-Hoc Explanations Only Exist for Simple Functions. I'll give an online presentation about this work next tuesday in @timvanerven.nl 's Theory of Interpretable AI Seminar: arxiv.org/abs/2508.11441 tverven.github.io/tiai-seminar/

0165

Reposted by Sebastian Bordt

Tim van Erven @timvanerven.nl · 30/09/2025

🚨 Workshop on the Theory of Explainable Machine Learning Call for ≤2 page extended abstract submissions by October 15 now open! 📍 Ellis UnConference in Copenhagen 📅 Dec. 2 🔗 More info: sites.google.com/view/theory-... @gunnark.bsky.social @ulrikeluxburg.bsky.social @emmanuelesposito.bsky.social

sites.google.com

Theory of XAI Workshop, Dec 2, 2025

Explainable AI (XAI) is now deployed across a wide range of settings, including high-stakes domains in which misleading explanations can cause real harm. For example, explanations are required by law ...

084

Reposted by Sebastian Bordt

Ulrike Luxburg @ulrikeluxburg.bsky.social · 17/09/2025

I am hiring PhD students and/or Postdocs, to work on the theory of explainable machine learning. Please apply through Ellis or IMPRS, deadlines end october/mid november. In particular: Women, where are you? Our community needs you!!! imprs.is.mpg.de/application ellis.eu/news/ellis-p...

02415

Reposted by Sebastian Bordt

Thomas Dietterich @tdietterich.bsky.social · 14/09/2025

We need new rules for publishing AI-generated research. The teams developing automated AI scientists have customarily submitted their papers to standard refereed venues (journals and conferences) and to arXiv. Often, acceptance has been treated as the dependent variable. 1/

48525

Reposted by Sebastian Bordt

Ben Recht @beenwrekt.bsky.social · 11/09/2025

This new center strikes the right tone in approaching the AI alignment problem. alignmentalignment.ai

alignmentalignment.ai

Center for the Alignment of AI Alignment Centers

We align the aligners

35914

Reposted by Sebastian Bordt

Johannes Zenn @johanneszenn.bsky.social · 29/08/2025

A new recording of our FridayTalks@Tübingen series is online! How much can we forget about Data Contamination? by @sbordt.bsky.social Watch here: youtu.be/T9Y5-rngOLg

youtu.be

How much can we forget about Data Contamination? - [Sebastian Bordt]

YouTube video by Friday Talks Tübingen

121

Reposted by Sebastian Bordt

Grace @gracekind.net · 19/07/2025

The stochastic parrot is now an IMO gold medalist parrot

2557

Sebastian Bordt @sbordt.bsky.social · 14/07/2025

I'm at #ICML in Vancouver this week, hit me up if you want to chat about pre-training experiments or explainable machine learning. You can find me at these posters: Tuesday: How Much Can We Forget about Data Contamination? icml.cc/virtual/2025...

111

Reposted by Sebastian Bordt

Ulrike Luxburg @ulrikeluxburg.bsky.social · 11/07/2025

Our #ICML position paper: #XAI is similar to applied statistics: it uses summary statistics in an attempt to answer real world questions. But authors need to state how concretely (!) their XAI statistics contributes to answer which concrete (!) question! arxiv.org/abs/2402.02870

062

Sebastian Bordt @sbordt.bsky.social · 10/07/2025

During the last couple of years, we have read a lot of papers on explainability and often felt that something was fundamentally missing🤔 This led us to write a position paper (accepted at #ICML2025) that attempts to identify the problem and to propose a solution. arxiv.org/abs/2402.02870 👇🧵

1125

Sebastian Bordt @sbordt.bsky.social · 08/07/2025

Have you ever wondered whether a few times of data contamination really lead to benchmark overfitting?🤔 Then our latest #ICML paper about the effect of data contamination on LLM evals might be for you!🚀 Paper: arxiv.org/abs/2410.03249 👇🧵

1121

Sebastian Bordt @sbordt.bsky.social · 16/05/2025

In explainable machine learning, we mostly have negative results for what post-hoc explanations cannot do. This work presents a surprisingly strong positive result for SHAP, showing that a simple sampling modification allows to reliably detect features that don't influence the model.

060

Reposted by Sebastian Bordt

Ulrike Luxburg @ulrikeluxburg.bsky.social · 05/05/2025

Finally made it to bluesky as well ...

2133

Reposted by Sebastian Bordt

Aaron Roth @aaroth.bsky.social · 20/03/2025

Is the distinction between "aleatoric" and "epistemic" uncertainty practically meaningful (or even well defined) in any real sense? Aleotoric uncertainty refers to irreducible unpredictability (e.g. unrealized randomness in nature) whereas epistemic refers to model uncertainty.

10343

Sebastian Bordt @sbordt.bsky.social · 18/03/2025

I really like coding with LLMs. This week Claude & ChatGPT convinced me my code was too slow. After 2 days of investigation, I think my code is just fine. Never again will I blindly trust you with my profiler logs!🤖

010

Sebastian Bordt @sbordt.bsky.social · 13/03/2025

I really like the new HTML preview on arxiv, but it somehow handles latex errors differently from PDF. I've been seeing lots of ICML error messages lately.

110

Sebastian Bordt @sbordt.bsky.social · 28/02/2025

can you draw me a dragon in tikz

030

Sebastian Bordt @sbordt.bsky.social · 25/01/2025

I just asked aistudio.google.com to write a review for a paper that we will submit to ICML. It's impressive. I believe with this tool, I could produce a mediocre paper review for almost any paper in less than 10 minutes (judged by the standard of reviews that we have at ML conferences).

020

Sebastian Bordt @sbordt.bsky.social · 20/01/2025

The chain of thought in DeepSeek-R1 is pretty impressive.

020

Reposted by Sebastian Bordt

Gautam Kamath @gautamkamath.com · 20/12/2024

ICML 2025 has some exciting changes. Here are two of my favorites. 1. Only 1 round of back-and-forth between authors & reviewers. The review process should not be an endless back and forth. It shouldn't be possible to get your paper accepted by exhausting reviewers.

2658

Sebastian Bordt @sbordt.bsky.social · 14/12/2024

Are you interested in data contamination and LLM benchmarks?🤖 Check out our poster today at the NeurIPS ATTRIB workshop (3-4:30pm)! 💡 TL;DR: In the large-data regime, a few times of data contamination matter less than you might think.

1101

Reposted by Sebastian Bordt

Sebastian Bordt @sbordt.bsky.social · 19/11/2024

Recent works have proposed to use publicly available Kaggle competitions to benchmark LLMs, most famously OpenAI's openai.com/index/mle-be.... In this blog, I show how to test LLMs for contamination with Kaggle competitions (of course, there is contamination). sbordt.substack.com/p/data-conta...