Lightnews — Scholar-powered news

Reposted by Tim van Erven

ELLIS @ellis.eu · 1d

How can we make AI explanations provably correct — not just convincing? 🤔

Join us for the Theory of Explainable Machine Learning Workshop, part of the ELLIS UnConference Copenhagen 🇩🇰 on Dec 2, co-located with #EurIPS.

🕒 Call for contributions open until Oct 15 (AoE)
🔗 eurips.cc/ellis

1 4 8

Reposted by Tim van Erven

ELLIS @ellis.eu · 4d

🎓 Ready to expand your horizons in #AI research? Do your PhD with 2 leading academic institutions across Europe and build your international network with the Academic Track in the #ELLISPhD Program.

Apply now via our central recruiting portal until Oct 31.

👉 All info: https://bit.ly/45DSe75

1 5

Reposted by Tim van Erven

Jessica Hullman @jessicahullman.bsky.social · 7d

Looking forward to talking about our work on the value of explanation for decision-making at this workshop

Gunnar König @gunnark.bsky.social · 7d

Interested in provable guarantees and fundamental limitations of XAI? Join us at the "Theory of Explainable AI" workshop Dec 2 in Copenhagen! @ellis.eu @euripsconf.bsky.social

Speakers: @jessicahullman.bsky.social @doloresromerom.bsky.social @tpimentel.bsky.social

Call for Contributions: Oct 15

Theory of XAI Workshop

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 ...

sites.google.com

3 11

Reposted by Tim van Erven

Dolores Romero Morales @doloresromerom.bsky.social · 7d

Are you coming ?

I will be talking about
#XAI #orms

Gunnar König @gunnark.bsky.social · 7d

Interested in provable guarantees and fundamental limitations of XAI? Join us at the "Theory of Explainable AI" workshop Dec 2 in Copenhagen! @ellis.eu @euripsconf.bsky.social

Speakers: @jessicahullman.bsky.social @doloresromerom.bsky.social @tpimentel.bsky.social

Call for Contributions: Oct 15

Theory of XAI Workshop

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 ...

sites.google.com

2 4

Tim van Erven @timvanerven.nl · 7d

Excellent bachelor's thesis by my student David van Batenburg with a mathematically rigorous treatment of the axiomatic characterization of Shapley values for feature attribution:

arxiv.org/abs/2510.03281

Clears up and corrects many math aspects that tripped me up when first learning about SHAP.

Mathematically rigorous proofs for Shapley explanations

Machine Learning is becoming increasingly more important in today's world. It is therefore very important to provide understanding of the decision-making process of machine-learning models. A popular ...

arxiv.org

6

Reposted by Tim van Erven

Gunnar König @gunnark.bsky.social · 7d

Interested in provable guarantees and fundamental limitations of XAI? Join us at the "Theory of Explainable AI" workshop Dec 2 in Copenhagen! @ellis.eu @euripsconf.bsky.social

Speakers: @jessicahullman.bsky.social @doloresromerom.bsky.social @tpimentel.bsky.social

Call for Contributions: Oct 15

Theory of XAI Workshop

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 ...

sites.google.com

5 8

Tim van Erven @timvanerven.nl · 7d

I have 2 open PhD positions on Mathematical Foundations for Explainable AI:

Position 1: werkenbij.uva.nl/en/vacancies... (apply by October 13, 2025)

Position 2: applications via the Ellis PhD Program: ellis.eu/news/ellis-p... by Oct. 31.

Both positions are equivalent (except for starting dates)

Vacancy — PhD Position on Mathematical Foundations for Explainable AI

Are you highly motivated to do PhD research in mathematical machine learning, with special emphasis on mathematical foundations for explainable AI? If yes, the Korteweg-de Vries Institute for Mathemat...

werkenbij.uva.nl

5 7

Tim van Erven @timvanerven.nl · 11d

And Theory results for Explainable Machine Learning!

Call for extended abstracts open until October 15, AoE.

sites.google.com/view/theory-...

Theory of XAI Workshop

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 ...

sites.google.com

1 3

Tim van Erven @timvanerven.nl · 12d

See you there!

2

Tim van Erven @timvanerven.nl · 14d

🚨 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

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 ...

sites.google.com

4 7

Reposted by Tim van Erven

Gokul Swamy @gokul.dev · 16d

Late, but arxiv.org/abs/0804.2996 is *incredible*, so many good lines (e.g., "This comes close to being an accusation of a false claim of priority for a false discovery of an untrue fact, which would be a rare triple-negative in the history of intellectual property disputes.").

The Epic Story of Maximum Likelihood

At a superficial level, the idea of maximum likelihood must be prehistoric: early hunters and gatherers may not have used the words ``method of maximum likelihood'' to describe their choice of where a...

arxiv.org

3 12

Reposted by Tim van Erven

Ulrike Luxburg @ulrikeluxburg.bsky.social · 28d

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...

15 23

Reposted by Tim van Erven

Peter Vamplew @amp1874.bsky.social · Sep 14

I reported a paper with fake citations to the Neurips editors a few months ago, and I've been informed Neurips will be introducing systematic checking of citations.

1 2 7

Tim van Erven @timvanerven.nl · Sep 9

Many interesting ideas in Tobias' talk today!

You can still watch the recording: youtu.be/IZ4m_II3DVI

2

Reposted by Tim van Erven

let-all.com @let-all.com · Sep 8

Wanna chat with an experienced learning theory researcher? We have open office hours online with four awesome folks, Surbhi Goel (@surbhigoel.bsky.social), Gautam Kamath (@gautamkamath.com), Ayush Sekhari, and Lydia Zakynthinou)!

Book a slot and ask them anything!
let-all.com/officehours....

2 5 11

Tim van Erven @timvanerven.nl · Sep 9

Happening today!

Tim van Erven @timvanerven.nl · Sep 3

🚨 The Theory of Interpretable AI Seminar is back after the summer!
🎙️ Tobias Leemann: On Identifiability & Representational Power of Post-Hoc Explanations
📅 Sept 9, 4PM CET / 10AM EST
📍 Online: uva-live.zoom.us/j/87120549999
🔗 Website: tverven.github.io/tiai-seminar/

3

Tim van Erven @timvanerven.nl · Sep 3

🚨 The Theory of Interpretable AI Seminar is back after the summer!
🎙️ Tobias Leemann: On Identifiability & Representational Power of Post-Hoc Explanations
📅 Sept 9, 4PM CET / 10AM EST
📍 Online: uva-live.zoom.us/j/87120549999
🔗 Website: tverven.github.io/tiai-seminar/

3

Tim van Erven @timvanerven.nl · Sep 1

The Netherlands now also has a call out to poach top international (non-EU) researchers whose academic freedom is threatened. Possibility to apply for 1M euro; need to be nominated by a Dutch research institution, which requires a recognizable strong profile. www.nwo.nl/en/calls/tulip-fund

Tulip Fund | NWO

Academic freedom is under mounting pressure on a global scale. The Tulip Fund offers international top researchers and top talents with their own line of research the opportunity to continue their research in the Netherlands.

www.nwo.nl

5 7

Tim van Erven @timvanerven.nl · Aug 29

Usually, this type of formulation is just to push for a lower acceptance rate, so I'm guessing that is the real motivation (which may be a valid reason, but it would have been better to just say so directly).

1 1

Reposted by Tim van Erven

Mark Riedl @markriedl.bsky.social · Aug 27

OpenAI is now in the moderation business

stop motion skeleton @jonchristian.net · Aug 27

NEW: After numerous tragedies, OpenAI says it's scanning users' conversations, escalating to human readers, and contacting law enforcement where necessary

futurism.com/openai-scann...

OpenAI Says It's Scanning Users' Conversations and Reporting Content to the Police

OpenAI has authorized itself to call law enforcement if users say threatening enough things when talking to ChatGPT.

futurism.com

2 13 17

Reposted by Tim van Erven

Timnit Gebru @timnitgebru.bsky.social · Aug 22

Lol, we need the "AI" that is killing the environment and guzzling untold amounts of resources to save the environment. This is 1984 type of marketing, like "ministry of peace" that is actually the war department.

Nature @nature.com · Aug 22

Without artificial-intelligence technologies, balancing human-caused greenhouse-gas emissions with carbon removals by 2050 is out of reach

go.nature.com/41LtWWk

Net zero needs AI — five actions to realize its promise

Without artificial-intelligence technologies, balancing human-caused greenhouse-gas emissions with carbon removals by 2050 is out of reach. Action in five areas is needed to keep this goal alive.

go.nature.com

17 240 690

Tim van Erven @timvanerven.nl · Jul 24

The policy is wise for future conferences, but I think punishing this year's authors is uncalled for: unless there is a policy in place to forbid these types of prompts, I would consider them more of a cheeky (and actually rather funny) way to protest against broken AI reviews than actual misconduct

1 7

Tim van Erven @timvanerven.nl · Jul 17

The unsustainability of long distance flights to conferences is a valid concern. Clearly, meeting international experts is important for high-level research, but dynamic regional events to supplement huge monolithic conferences might even make that easier. We need more experiments like EurIPS asap.

Pierre Marion @pierremarion.bsky.social · Jul 17

🌍 Would be better if authors were allowed to present at officially endorsed hubs or online instead — ensuring fair and equitable participation, and ultimately creating a better NeurIPS for everyone.

Interesting in knowing more: read our full opinion piece ⬇️. docs.google.com/document/d/1...
4/4

Towards decentralized ML conferences

Towards decentralized ML conferences Pierre Marion July 2025 Abstract: Large ML conferences play a central role in our community, by providing a rigorous review process and a venue for meaningful di...

docs.google.com

1 3 11

Reposted by Tim van Erven

EurIPS Conference @euripsconf.bsky.social · Jul 16

EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅

EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu

eurips.cc

2 70 140

Reposted by Tim van Erven

Ben Recht @beenwrekt.bsky.social · Jul 3

The NeurIPS paper checklist corroborates the bureaucratic theory of statistics.

Standard error of what now?

The NeurIPS checklist corroborates the bureaucratic theory of statistics.

www.argmin.net

5 13 64