Lightnews — Scholar-powered news

Oliver Eberle @eberleoliver.bsky.social · 19d

🥳 Super happy to have our work on multi-concept feature descriptions accepted at #NeurIPS2025!

Laura Kopf @lkopf.bsky.social · 19d

Happy to share that our PRISM paper has been accepted at #NeurIPS2025 🎉

In this work, we introduce a multi-concept feature description framework that can identify and score polysemantic features.

📄 Paper: arxiv.org/abs/2506.15538

#NeurIPS #MechInterp #XAI

1 12

Oliver Eberle @eberleoliver.bsky.social · Jul 16

📯 Come visit our #ICML25 Spotlight Poster and meet @taylorwwebb.bsky.social to discuss our work: "Toward an Algorithmic Evaluation and Understanding of Generative AI."

Paper: openreview.net/forum?id=eax...
Poster: icml.cc/media/Poster...

Position: We Need An Algorithmic Understanding of Generative AI

What algorithms do LLMs actually learn and use to solve problems? Studies addressing this question are sparse, as research priorities are focused on improving performance through scale, leaving a...

openreview.net

1 7

Oliver Eberle @eberleoliver.bsky.social · Jun 20

Our position paper on algorithmic explanations is out—excited to share it! 🙌

Proud of this collaborative effort toward a scientifically grounded understanding of generative AI.

@tuberlin.bsky.social @bifold.berlin @msftresearch.bsky.social @UCSD & @UCLA

1 8 17

Oliver Eberle @eberleoliver.bsky.social · Jun 19

🚨 New preprint! Excited to share our work on extracting and evaluating the potentially many feature descriptions of language models

👉 arxiv.org/abs/2506.15538

Laura Kopf @lkopf.bsky.social · Jun 19

🔍 When do neurons encode multiple concepts?

We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity.

📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
arxiv.org/abs/2506.15538

🧵 (1/7)

4 18

Oliver Eberle @eberleoliver.bsky.social · May 27

"Who owns the tools that shape our understanding of the past?"

Large language models that power AI should be publicly owned | Letter

Letters: The future of public knowledge rests on building open-access LLMs driven by ethics rather than profit, writes Prof Dr Matteo Valleriani

www.theguardian.com

2 6

Reposted by Oliver Eberle

BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · May 15

THE NEVERENDING CURE – new exhibition by kennedy + swan
🗓 May 28 | 🕕 6PM | 📍 UNI_VERSUM, TU Berlin

Art + AI + Snacks = A night not to miss!
With intros by BIFOLD scientists + artists.

www.bifold.berlin/news-events/...

#ArtOfEntanglement #ArtAndScience
@tuberlin.bsky.social
#ScheringStiftung

3 4

Reposted by Oliver Eberle

Lorenz Linhardt @lorenzlinhardt.bsky.social · May 3

🖼️ At the Re-Align workshop, @tomneuhaeuser.bsky.social and I presented "Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments", joint work with Lenka Tětková and @eberleoliver.bsky.social .
📃 arxiv.org/abs/2504.07965

Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments

Small and mid-sized generative language models have gained increasing attention. Their size and availability make them amenable to being analyzed at a behavioral as well as a representational level, a...

arxiv.org

1 3

Oliver Eberle @eberleoliver.bsky.social · Mar 4

📜 🎉 Happy to announce our workshop "AI-based Methods for the Humanities"! Bringing together #ML and #Humanities researchers to discuss frontiers in #DigitalHumanities, #NLP, #XAI and more!

Hosted together with Matteo Valleriani and
@bifold.berlin @tuberlin.bsky.social @mpiwg.bsky.social

BIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · Mar 4

Call for Papers / #AI & #DigitalHumanities -> Workshop "AI-based Methods for the Humanities" (Berlin, September 23 to 24, 2025)

Deadline: April 1, 2025 (rolling evaluations until slots are filled)
www.bifold.berlin/news-events/...

#DigitalHumanities #DH #HistSci #AI #CfP

3 9

Reposted by Oliver Eberle

Max Planck Institute for the History of Science @mpiwg.bsky.social · Feb 26

Next up in our Institute’s Colloquium Series “History of Science in Public”: Kate Crawford @katecrawford.bsky.social will talk on "Mapping #AI: How to See Planetary-Scale #ArtificialIntelligence.”

🗓️ Mar 25, 2025 (14:00 CET)
🔗 bitly.cx/m0KeS
📍 relocated: MPIWG Main conference room

#HistSci #SciComm

Poster showing the MPIWG Institute’s Colloquium 2024–25 program.

1 5 15

Oliver Eberle @eberleoliver.bsky.social · Feb 3

Danke für den Austausch @tuberlin.bsky.social – es bleibt spannend! 😉

Technische Universität Berlin @tuberlin.bsky.social · Jan 31

Zur vollständigen Pressemitteilung 👉 www.tu.berlin/go1043/n64996/

TU Berlin: Expert*innen zum jüngsten Erfolg von „DeepSeek“

Expert*innen der TU Berlin über den Unterschied zwischen Open-Source-Anwendungen wie „DeepSeek" und anderen LLMs sowie der Rolle Europas bei der Entwicklung von Künstlicher Intelligenz (KI)

www.tu.berlin

1 6

Oliver Eberle @eberleoliver.bsky.social · Dec 27

Work with Jochen Büttner, Hassan El-Hajj, Grégoire Montavon, Klaus-Robert Müller, and Matteo Valleriani.

#ScienceAdvances
#DigitalHumanities
#HistSci

3

Oliver Eberle @eberleoliver.bsky.social · Dec 27

📜 History repeats itself: We investigated how early modern communities have embraced scholarly advancements, reshaping scientific views and exploring scientific roots amidst a changing world.

www.science.org/doi/10.1126/...

@mpiwg.bsky.social @tuberlin.bsky.social @bifold.berlin @science.org

1 3 15

Reposted by Oliver Eberle

Uwe Ohler @uweohler.bsky.social · Nov 19

First #jobalert on Bluesky! Postdoc (or PhD position with strong ML background), for a joint project with Gregoire Montavon’s lab at #BIFOLD #TU-Berlin .

Topic is explainable AI /ML for self supervised LLMs in multi/spatial omics & gene regulation.

www.jobs.tu-berlin.de/stellenaussc...

Stellenausschreibung IV-618/24: Research Assistant - salary grade E13 TV-L Berliner Hochschulen - For qualification – Stellenausschreibungen der Technischen Universität Berlin

www.jobs.tu-berlin.de

1 10 18

Oliver Eberle @eberleoliver.bsky.social · Nov 26

Here a gathered a complementary Explainable AI/Interpretability starter pack ;) Nice to see so many of us here now!

2

Oliver Eberle @eberleoliver.bsky.social · Nov 26

Welcome, you should be in it now :)

1 1

Reposted by Oliver Eberle

Stephanie Brandl @stephaniebrandl.bsky.social · Mar 1

I am thrilled to share that our paper "Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations" was accepted to LREC-COLING
📜 arxiv.org/pdf/2402.19133…

We analyse low-cost eye-tracking data as an alternative to human rationale annotations when evaluating XAI methods.

2 9

Oliver Eberle @eberleoliver.bsky.social · Nov 24

17 5 25