Kristian Kersting
@kerstingaiml.bsky.social
AI Prof at TU Darmstadt, Founding Co-Director Hessian.AI, DFKI, AAAI/EurAI/AAIA/ELLIS Fellow, AAAI24 Ass. PC CoChair, Fmr. PC CoChair UAI, ECML PKDD, Invest. @Aleph__Alpha, Fmr. AI Column German Newspaper Welt (am Sonntag)
🚀 Join @tuda.bsky.social and @hessianai.bsky.social as Professor for Ethical & Safe AI to advance the algorithmic foundations of ethical and safe AI and to shape “Reasonable AI."
Apply now and make an impact where AI meets society.
👉 buff.ly/bIvq7Mb
Apply now and make an impact where AI meets society.
👉 buff.ly/bIvq7Mb
November 8, 2025 at 2:29 PM
🚀 Join @tuda.bsky.social and @hessianai.bsky.social as Professor for Ethical & Safe AI to advance the algorithmic foundations of ethical and safe AI and to shape “Reasonable AI."
Apply now and make an impact where AI meets society.
👉 buff.ly/bIvq7Mb
Apply now and make an impact where AI meets society.
👉 buff.ly/bIvq7Mb
Reposted by Kristian Kersting
We show applications to long-term outcomes and decision making, developing our works on 'causal parrots' openreview.net/pdf?id=tv46t... and meta-causality openreview.net/pdf?id=J9Vog... .
Thanks to my coauthors @philosotim.bsky.social, @devendradhami.bsky.social and @kerstingaiml.bsky.social! 2/4
Thanks to my coauthors @philosotim.bsky.social, @devendradhami.bsky.social and @kerstingaiml.bsky.social! 2/4
openreview.net
November 4, 2025 at 12:07 PM
We show applications to long-term outcomes and decision making, developing our works on 'causal parrots' openreview.net/pdf?id=tv46t... and meta-causality openreview.net/pdf?id=J9Vog... .
Thanks to my coauthors @philosotim.bsky.social, @devendradhami.bsky.social and @kerstingaiml.bsky.social! 2/4
Thanks to my coauthors @philosotim.bsky.social, @devendradhami.bsky.social and @kerstingaiml.bsky.social! 2/4
Reposted by Kristian Kersting
As part of ELIZA, doctoral researchers join a vibrant AI community across Germany, supervised by leading scientists including @igurevych.bsky.social, @kerstingaiml.bsky.social, Jonas Peters & Mira Mezini.
(3/3)
#PhD #AIResearch #MachineLearning #NLP #ELIZA #UKPLab #TUDarmstadt
(3/3)
#PhD #AIResearch #MachineLearning #NLP #ELIZA #UKPLab #TUDarmstadt
October 27, 2025 at 9:34 AM
As part of ELIZA, doctoral researchers join a vibrant AI community across Germany, supervised by leading scientists including @igurevych.bsky.social, @kerstingaiml.bsky.social, Jonas Peters & Mira Mezini.
(3/3)
#PhD #AIResearch #MachineLearning #NLP #ELIZA #UKPLab #TUDarmstadt
(3/3)
#PhD #AIResearch #MachineLearning #NLP #ELIZA #UKPLab #TUDarmstadt
Reposted by Kristian Kersting
10 (zehn !!1!) Jahre ist der NR-Talk von @spielkamp.bsky.social , @nettwerkerin.bsky.social, @kerstingaiml.bsky.social und mir her, um über Algorithmen & Kontrolle zu reden.
Es war einer der Impulse für @algorithmwatch.org, bei mir Anfang eines kleinen ;-) Umwegs zur KI. But: Finally there!
Es war einer der Impulse für @algorithmwatch.org, bei mir Anfang eines kleinen ;-) Umwegs zur KI. But: Finally there!
September 9, 2025 at 2:32 PM
10 (zehn !!1!) Jahre ist der NR-Talk von @spielkamp.bsky.social , @nettwerkerin.bsky.social, @kerstingaiml.bsky.social und mir her, um über Algorithmen & Kontrolle zu reden.
Es war einer der Impulse für @algorithmwatch.org, bei mir Anfang eines kleinen ;-) Umwegs zur KI. But: Finally there!
Es war einer der Impulse für @algorithmwatch.org, bei mir Anfang eines kleinen ;-) Umwegs zur KI. But: Finally there!
Reposted by Kristian Kersting
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
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
July 16, 2025 at 10:01 PM
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
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
Reposted by Kristian Kersting
📢 Present your NeurIPS paper in Europe!
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
July 16, 2025 at 11:00 PM
📢 Present your NeurIPS paper in Europe!
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date:
📅 Dec 2–7, 2025
📍 Copenhagen 🇩🇰
🔗eurips.cc
#EurIPS
@euripsconf.bsky.social
Reposted by Kristian Kersting
Can concept-based models handle complex, object-rich images? We think so! Meet Object-Centric Concept Bottlenecks (OCB) — adding object-awareness to interpretable AI. Led by David Steinmann w/ @toniwuest.bsky.social & @kerstingaiml.bsky.social .
📄 arxiv.org/abs/2505.244...
#AI #XAI #NeSy #CBM #ML
📄 arxiv.org/abs/2505.244...
#AI #XAI #NeSy #CBM #ML
July 7, 2025 at 3:55 PM
Can concept-based models handle complex, object-rich images? We think so! Meet Object-Centric Concept Bottlenecks (OCB) — adding object-awareness to interpretable AI. Led by David Steinmann w/ @toniwuest.bsky.social & @kerstingaiml.bsky.social .
📄 arxiv.org/abs/2505.244...
#AI #XAI #NeSy #CBM #ML
📄 arxiv.org/abs/2505.244...
#AI #XAI #NeSy #CBM #ML
Reposted by Kristian Kersting
@kerstingaiml.bsky.social (TU Darmstadt), Frauke Kreuter (LMU Munich, MCML, @zuseschoolrelai.bsky.social ), Mira Mezini (TU Darmstadt), @igurevych.bsky.social (TU Darmstadt, @athenecenter.bsky.social), [...]
(5/🧵)
(5/🧵)
July 15, 2025 at 9:24 AM
@kerstingaiml.bsky.social (TU Darmstadt), Frauke Kreuter (LMU Munich, MCML, @zuseschoolrelai.bsky.social ), Mira Mezini (TU Darmstadt), @igurevych.bsky.social (TU Darmstadt, @athenecenter.bsky.social), [...]
(5/🧵)
(5/🧵)
Reposted by Kristian Kersting
@kerstingaiml.bsky.social ist Professor für KI und Maschinelles Lernen am @cs-tudarmstadt.bsky.social der @tuda.bsky.social und leitet dort das Artificial Intelligence and Machine Learning Lab (AIML).
June 20, 2025 at 10:44 AM
@kerstingaiml.bsky.social ist Professor für KI und Maschinelles Lernen am @cs-tudarmstadt.bsky.social der @tuda.bsky.social und leitet dort das Artificial Intelligence and Machine Learning Lab (AIML).
🙏 for the invitation to give a talk at the Causal Neuro-Symbolic AI (Causal-NeSy) Workshop at ESWC. Integrating causality, neuro-symbolic reasoning, and machine learning to build more robust, interpretable, and generalizable AI systems is so important.
June 1, 2025 at 1:25 PM
🙏 for the invitation to give a talk at the Causal Neuro-Symbolic AI (Causal-NeSy) Workshop at ESWC. Integrating causality, neuro-symbolic reasoning, and machine learning to build more robust, interpretable, and generalizable AI systems is so important.
Reposted by Kristian Kersting
»Diagnostic Reasoning in Natural Language: Computational Model and Application« by @nilsdy.bsky.social, Matej Zečević, Ilia Kuznetsov, @kerstingaiml.bsky.social, @igurevych.bsky.social
📄 arxiv.org/abs/2409.05367
(8/🧵)
📄 arxiv.org/abs/2409.05367
(8/🧵)
Diagnostic Reasoning in Natural Language: Computational Model and Application
Diagnostic reasoning is a key component of expert work in many domains. It is a hard, time-consuming activity that requires expertise, and AI research has investigated the ways automated systems can s...
arxiv.org
May 27, 2025 at 1:21 PM
»Diagnostic Reasoning in Natural Language: Computational Model and Application« by @nilsdy.bsky.social, Matej Zečević, Ilia Kuznetsov, @kerstingaiml.bsky.social, @igurevych.bsky.social
📄 arxiv.org/abs/2409.05367
(8/🧵)
📄 arxiv.org/abs/2409.05367
(8/🧵)
🚀 TU Darmstadt leads the new Cluster of Excellence "Reasonable AI" – advancing trustworthy, efficient & adaptive AI grounded in common sense. A big thank you to the entire team, the university, and the state of Hesse for their tremendous work & support!
Reasonable and safe: The future of artificial intelligence
The researchers in the new Cluster of Excellence “Reasonable Artificial Intelligence” (RAI) , which is headed by TU Darmstadt, are carrying out research into a new generation of artificial…
buff.ly
May 24, 2025 at 9:10 AM
🚀 TU Darmstadt leads the new Cluster of Excellence "Reasonable AI" – advancing trustworthy, efficient & adaptive AI grounded in common sense. A big thank you to the entire team, the university, and the state of Hesse for their tremendous work & support!
Reposted by Kristian Kersting
👉 Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
Joint work with folks from TU Darmstadt, TU Munich, @kathaem.bsky.social, @jlibovicky.bsky.social, @mbrackaiml.bsky.social, @kerstingaiml.bsky.social
arxiv.org/abs/2401.16092
Joint work with folks from TU Darmstadt, TU Munich, @kathaem.bsky.social, @jlibovicky.bsky.social, @mbrackaiml.bsky.social, @kerstingaiml.bsky.social
arxiv.org/abs/2401.16092
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
Text-to-image generation models have recently achieved astonishing results in image quality, flexibility, and text alignment, and are consequently employed in a fast-growing number of applications. Th...
arxiv.org
May 21, 2025 at 1:13 PM
👉 Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
Joint work with folks from TU Darmstadt, TU Munich, @kathaem.bsky.social, @jlibovicky.bsky.social, @mbrackaiml.bsky.social, @kerstingaiml.bsky.social
arxiv.org/abs/2401.16092
Joint work with folks from TU Darmstadt, TU Munich, @kathaem.bsky.social, @jlibovicky.bsky.social, @mbrackaiml.bsky.social, @kerstingaiml.bsky.social
arxiv.org/abs/2401.16092
Wer tiefer einsteigen will: Im Podcast „Eine letzte Chance“ spricht @thinkBTO über das Digitalministerium – mit Bezug zu unserem Whitepaper zur digitalen Staatlichkeit.
Hören lohnt sich! 🎧
👉 podcasts.apple.com/de/podcast/b...
Hören lohnt sich! 🎧
👉 podcasts.apple.com/de/podcast/b...
Eine letzte Chance
Podcast-Folge · bto – der Ökonomie-Podcast von Dr. Daniel Stelter · 11.05.2025 · 1 Std. 24 Min.
podcasts.apple.com
May 11, 2025 at 7:00 PM
Wer tiefer einsteigen will: Im Podcast „Eine letzte Chance“ spricht @thinkBTO über das Digitalministerium – mit Bezug zu unserem Whitepaper zur digitalen Staatlichkeit.
Hören lohnt sich! 🎧
👉 podcasts.apple.com/de/podcast/b...
Hören lohnt sich! 🎧
👉 podcasts.apple.com/de/podcast/b...
Ich freue mich, in der aktuellen Beyond the Obvious-Kolumne von @thinkBTO im @handelsblatt zum neuen Digitalministerium aufzutauchen. Digitalisierung braucht endlich Rückenwind – jetzt kommt es auf kluge Umsetzung und echten Gestaltungswillen an.
👉
👉
Beyond the obvious: Digitalisierung „made in Europe“ ist die letzte Chance
Dass es in den 1980er-Jahren gelungen ist, den Mobilfunk-Standard GSM als globalen Standard zu etablieren, lag am gemeinsamen europäischen Vorgehen und einer Entscheidung.
buff.ly
May 11, 2025 at 3:34 PM
Ich freue mich, in der aktuellen Beyond the Obvious-Kolumne von @thinkBTO im @handelsblatt zum neuen Digitalministerium aufzutauchen. Digitalisierung braucht endlich Rückenwind – jetzt kommt es auf kluge Umsetzung und echten Gestaltungswillen an.
👉
👉
Reposted by Kristian Kersting
Excited to share that our paper got accepted at #ICML2025!! 🎉
We challenge Vision-Language Models like OpenAI’s o1 with Bongard problems, classic visual reasoning challenges and uncover surprising shortcomings.
Check out the paper: arxiv.org/abs/2410.19546
& read more below 👇
We challenge Vision-Language Models like OpenAI’s o1 with Bongard problems, classic visual reasoning challenges and uncover surprising shortcomings.
Check out the paper: arxiv.org/abs/2410.19546
& read more below 👇
May 2, 2025 at 7:48 AM
Excited to share that our paper got accepted at #ICML2025!! 🎉
We challenge Vision-Language Models like OpenAI’s o1 with Bongard problems, classic visual reasoning challenges and uncover surprising shortcomings.
Check out the paper: arxiv.org/abs/2410.19546
& read more below 👇
We challenge Vision-Language Models like OpenAI’s o1 with Bongard problems, classic visual reasoning challenges and uncover surprising shortcomings.
Check out the paper: arxiv.org/abs/2410.19546
& read more below 👇
Reposted by Kristian Kersting
Consider following the authors Indraneil Paul (@ineil77.bsky.social), Haoyi Yang, Goran Glavaš, Kristian Kersting (@kerstingaiml.bsky.social) & Iryna Gurevych (@igurevych.bsky.social) if you are interested in more information or an exchange of ideas. (7/7)
See you this week in Singapore! #ICLR2025
See you this week in Singapore! #ICLR2025
April 22, 2025 at 9:08 AM
Consider following the authors Indraneil Paul (@ineil77.bsky.social), Haoyi Yang, Goran Glavaš, Kristian Kersting (@kerstingaiml.bsky.social) & Iryna Gurevych (@igurevych.bsky.social) if you are interested in more information or an exchange of ideas. (7/7)
See you this week in Singapore! #ICLR2025
See you this week in Singapore! #ICLR2025
Reposted by Kristian Kersting
I'm excited to present our spotlight on meta-causal models at #ICLR2025 next week.
We model evolving causal graphs in dynamic systems. Applications to inference and attribution of agent actions. Paper: openreview.net/forum?id=J9V...
Visit our poster #441 during the Sat 3pm session.
We model evolving causal graphs in dynamic systems. Applications to inference and attribution of agent actions. Paper: openreview.net/forum?id=J9V...
Visit our poster #441 during the Sat 3pm session.
April 17, 2025 at 5:56 PM
I'm excited to present our spotlight on meta-causal models at #ICLR2025 next week.
We model evolving causal graphs in dynamic systems. Applications to inference and attribution of agent actions. Paper: openreview.net/forum?id=J9V...
Visit our poster #441 during the Sat 3pm session.
We model evolving causal graphs in dynamic systems. Applications to inference and attribution of agent actions. Paper: openreview.net/forum?id=J9V...
Visit our poster #441 during the Sat 3pm session.
Reposted by Kristian Kersting
»ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding« by Indraneil Paul (@ineil77.bsky.social), Haoyi Yang, Goran Glavaš, Kristian Kersting (@kerstingaiml.bsky.social) & Iryna Gurevych (@igurevych.bsky.social)
📄https://openreview.net/forum?id=VYvxrD7aS0 (3/🧵)
📄https://openreview.net/forum?id=VYvxrD7aS0 (3/🧵)
ObscuraCoder: Powering Efficient Code LM Pre-Training Via...
Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes in data sourcing...
openreview.net
April 16, 2025 at 7:50 AM
»ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding« by Indraneil Paul (@ineil77.bsky.social), Haoyi Yang, Goran Glavaš, Kristian Kersting (@kerstingaiml.bsky.social) & Iryna Gurevych (@igurevych.bsky.social)
📄https://openreview.net/forum?id=VYvxrD7aS0 (3/🧵)
📄https://openreview.net/forum?id=VYvxrD7aS0 (3/🧵)
Reposted by Kristian Kersting
xLSTM for time series with Granger causality: arxiv.org/abs/2502.09981
xLSTM again shows superb performance at time series analysis.
"Our experimental evaluations on three datasets demonstrate the overall efficacy of our proposed GC-xLSTM model."
xLSTM again shows superb performance at time series analysis.
"Our experimental evaluations on three datasets demonstrate the overall efficacy of our proposed GC-xLSTM model."
Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
Causality in time series can be difficult to determine, especially in the presence of non-linear dependencies. The concept of Granger causality helps analyze potential relationships between variables,...
arxiv.org
February 17, 2025 at 6:18 AM
xLSTM for time series with Granger causality: arxiv.org/abs/2502.09981
xLSTM again shows superb performance at time series analysis.
"Our experimental evaluations on three datasets demonstrate the overall efficacy of our proposed GC-xLSTM model."
xLSTM again shows superb performance at time series analysis.
"Our experimental evaluations on three datasets demonstrate the overall efficacy of our proposed GC-xLSTM model."
🚨 Are you a student passionate about innovation, technology, and building connections? This is your chance to attend leading events connecting female researchers in computer science and engineering 🧳
FSTA_2025
Are you a student passionate about innovation, technology, and building connections? This is your chance to attend leading events connecting female researchers in computer science and engineering—we…
buff.ly
February 16, 2025 at 4:34 PM
🚨 Are you a student passionate about innovation, technology, and building connections? This is your chance to attend leading events connecting female researchers in computer science and engineering 🧳
Doch, wir müssen uns Sorgen machen – aber können handeln 💪 DeepSeek-äquivalente Modelle sind nur mit Investitionen in Teams, Infrastruktur & Daten möglich. Ich freue mich daher über den Austausch mit dem tollen Fraunhofer-Teams der bereits startet 🚀
Künstliche Intelligenz: „Wir müssen uns beim Thema KI keine Sorgen machen“
Der Präsident der Fraunhofer-Gesellschaft, Holger Hanselka, sieht in dem Thema KI große Chancen für die deutsche Wirtschaft. Mit der richtigen Spezialisierung.
www.wiwo.de
February 9, 2025 at 5:04 PM
Doch, wir müssen uns Sorgen machen – aber können handeln 💪 DeepSeek-äquivalente Modelle sind nur mit Investitionen in Teams, Infrastruktur & Daten möglich. Ich freue mich daher über den Austausch mit dem tollen Fraunhofer-Teams der bereits startet 🚀
🚀 Exakt, wir sind bereit, die nächste Stufe im KI-Ausbau zu zünden! TU Darmstadt, hessian.AI & viele weitere Standorte in 🇩🇪 treiben Forschung & Anwendung voran. Zusammen, auch mit der Industrie, kann viel passieren.
Die Berichte über #Stargate und #Deepseek sieht er als Weckruf für Deutschland und Europa: der Vorsitzende unserer Fokusgruppe KI, Wolfgang Lehner. Was jetzt zu tun ist, um #KI hier voranzubringen, erklärt Lehner im Interview mit @mweisskopf.bsky.social von @table.media table.media/research/ana...
Wolfgang Lehner: Wie man bei KI die nächste Stufe zünden kann
Der Vorsitzende der KI-Fokusgruppe des Wissenschaftsrats, Wolfgang Lehner, betrachtet Berichte über Deepseek und Stargate als Weckruf.
table.media
February 7, 2025 at 3:27 PM
🚀 Exakt, wir sind bereit, die nächste Stufe im KI-Ausbau zu zünden! TU Darmstadt, hessian.AI & viele weitere Standorte in 🇩🇪 treiben Forschung & Anwendung voran. Zusammen, auch mit der Industrie, kann viel passieren.
ChatGPT-Entwickler: Open AI eröffnet erstes Büro in Deutschland via @faznet
February 6, 2025 at 9:54 PM
ChatGPT-Entwickler: Open AI eröffnet erstes Büro in Deutschland via @faznet
Reposted by Kristian Kersting
🍰Super proud of our newest work:
“The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation” - arxiv.org/abs/2502.03038
🍰We extend Yann LeCun’s AI cake analogy to relate socio-technical outcomes to the AI life-cycle!
More details below ⬇️ 1/4
“The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation” - arxiv.org/abs/2502.03038
🍰We extend Yann LeCun’s AI cake analogy to relate socio-technical outcomes to the AI life-cycle!
More details below ⬇️ 1/4
February 6, 2025 at 2:38 PM
🍰Super proud of our newest work:
“The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation” - arxiv.org/abs/2502.03038
🍰We extend Yann LeCun’s AI cake analogy to relate socio-technical outcomes to the AI life-cycle!
More details below ⬇️ 1/4
“The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation” - arxiv.org/abs/2502.03038
🍰We extend Yann LeCun’s AI cake analogy to relate socio-technical outcomes to the AI life-cycle!
More details below ⬇️ 1/4