Beatrix M. G. Nielsen
@beatrixmgn.bsky.social
PhD student in machine learning at DTU, Copenhagen.
Especially interested in model representations.
Especially interested in model representations.
Reposted by Beatrix M. G. Nielsen
The promise of AI chat assistants: they solve 90% of the problems users have (by looking up the docs and telling them)
My reality: need to spend 10 minutes trying to get to a human, to solve an issue I need customer support to look into
Around minute 8 I sign up to a competitor
My reality: need to spend 10 minutes trying to get to a human, to solve an issue I need customer support to look into
Around minute 8 I sign up to a competitor
November 4, 2025 at 4:14 PM
The promise of AI chat assistants: they solve 90% of the problems users have (by looking up the docs and telling them)
My reality: need to spend 10 minutes trying to get to a human, to solve an issue I need customer support to look into
Around minute 8 I sign up to a competitor
My reality: need to spend 10 minutes trying to get to a human, to solve an issue I need customer support to look into
Around minute 8 I sign up to a competitor
I am happy to announce that our article "When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective" has been accepted at NeurIPS 2025! 🎉 arxiv.org/abs/2506.037...
Details below 👇
Details below 👇
When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
When and why representations learned by different deep neural networks are similar is an active research topic. We choose to address these questions from the perspective of identifiability theory, whi...
arxiv.org
October 21, 2025 at 5:45 AM
I am happy to announce that our article "When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective" has been accepted at NeurIPS 2025! 🎉 arxiv.org/abs/2506.037...
Details below 👇
Details below 👇
Reposted by Beatrix M. G. Nielsen
Andrej Karpathy’s take on AI coding agents feels grounded. The industry’s chasing full autonomy when models still hallucinate too much.
Agents that churn out a thousand lines of code leave you either blindly trusting them or slogging through reviews. These tools should embrace their fallibility.
Agents that churn out a thousand lines of code leave you either blindly trusting them or slogging through reviews. These tools should embrace their fallibility.
October 19, 2025 at 4:33 PM
Andrej Karpathy’s take on AI coding agents feels grounded. The industry’s chasing full autonomy when models still hallucinate too much.
Agents that churn out a thousand lines of code leave you either blindly trusting them or slogging through reviews. These tools should embrace their fallibility.
Agents that churn out a thousand lines of code leave you either blindly trusting them or slogging through reviews. These tools should embrace their fallibility.
Good news everyone!
I’ll be presenting the paper I did with Marco and Iuri "Prediction Hubs are Context-Informed Frequent tokens in LLMs" at the ELLIS UnConference on December 2nd in Copenhagen. arxiv.org/abs/2502.10201
I’ll be presenting the paper I did with Marco and Iuri "Prediction Hubs are Context-Informed Frequent tokens in LLMs" at the ELLIS UnConference on December 2nd in Copenhagen. arxiv.org/abs/2502.10201
Prediction hubs are context-informed frequent tokens in LLMs
Hubness, the tendency for a few points to be among the nearest neighbours of a disproportionate number of other points, commonly arises when applying standard distance measures to high-dimensional dat...
arxiv.org
October 15, 2025 at 6:40 AM
Good news everyone!
I’ll be presenting the paper I did with Marco and Iuri "Prediction Hubs are Context-Informed Frequent tokens in LLMs" at the ELLIS UnConference on December 2nd in Copenhagen. arxiv.org/abs/2502.10201
I’ll be presenting the paper I did with Marco and Iuri "Prediction Hubs are Context-Informed Frequent tokens in LLMs" at the ELLIS UnConference on December 2nd in Copenhagen. arxiv.org/abs/2502.10201
Reposted by Beatrix M. G. Nielsen
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
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
October 13, 2025 at 9:10 AM
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
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
Reposted by Beatrix M. G. Nielsen
🚀 Applications for the @ellis.eu PhD Program 2025 are now open!
Join Europe’s leading network in AI & Machine Learning research,🌍
📚 Choose among three collaboration pathways: Academic, Industry, or Interdisciplinary. 🗓️ Apply by Oct 31, 2025 🔗 ellis.eu/phd-program
Join Europe’s leading network in AI & Machine Learning research,🌍
📚 Choose among three collaboration pathways: Academic, Industry, or Interdisciplinary. 🗓️ Apply by Oct 31, 2025 🔗 ellis.eu/phd-program
October 7, 2025 at 11:19 AM
🚀 Applications for the @ellis.eu PhD Program 2025 are now open!
Join Europe’s leading network in AI & Machine Learning research,🌍
📚 Choose among three collaboration pathways: Academic, Industry, or Interdisciplinary. 🗓️ Apply by Oct 31, 2025 🔗 ellis.eu/phd-program
Join Europe’s leading network in AI & Machine Learning research,🌍
📚 Choose among three collaboration pathways: Academic, Industry, or Interdisciplinary. 🗓️ Apply by Oct 31, 2025 🔗 ellis.eu/phd-program
Reposted by Beatrix M. G. Nielsen
✨ EurIPS registration is now open! Get one of the 1,500 tickets available. 500 tickets are discounted for students 🎓.
In Copenhagen 🇩🇰 on Dec 2-7, 2025.
❗ Entrance to the ELLIS UnConference is free with a #EurIPS ticket.
Get your ticket now: https://eurips.cc/
@euripsconf.bsky.social
In Copenhagen 🇩🇰 on Dec 2-7, 2025.
❗ Entrance to the ELLIS UnConference is free with a #EurIPS ticket.
Get your ticket now: https://eurips.cc/
@euripsconf.bsky.social
October 2, 2025 at 9:23 AM
✨ EurIPS registration is now open! Get one of the 1,500 tickets available. 500 tickets are discounted for students 🎓.
In Copenhagen 🇩🇰 on Dec 2-7, 2025.
❗ Entrance to the ELLIS UnConference is free with a #EurIPS ticket.
Get your ticket now: https://eurips.cc/
@euripsconf.bsky.social
In Copenhagen 🇩🇰 on Dec 2-7, 2025.
❗ Entrance to the ELLIS UnConference is free with a #EurIPS ticket.
Get your ticket now: https://eurips.cc/
@euripsconf.bsky.social
Reposted by Beatrix M. G. Nielsen
🏹 Job alert: Several fully-funded open Post-Doc positions for 'AI for Scientific Discovery in Physics' at @unituebingen.bsky.social
📍 Tübingen 🇩🇪
📅 Apply by Oct 28th (unless filled before)
🔗 ellis.eu/jobs/ai-for-...
📍 Tübingen 🇩🇪
📅 Apply by Oct 28th (unless filled before)
🔗 ellis.eu/jobs/ai-for-...
AI for Scientific Discovery in Physics
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...
ellis.eu
September 30, 2025 at 2:42 PM
🏹 Job alert: Several fully-funded open Post-Doc positions for 'AI for Scientific Discovery in Physics' at @unituebingen.bsky.social
📍 Tübingen 🇩🇪
📅 Apply by Oct 28th (unless filled before)
🔗 ellis.eu/jobs/ai-for-...
📍 Tübingen 🇩🇪
📅 Apply by Oct 28th (unless filled before)
🔗 ellis.eu/jobs/ai-for-...
Reposted by Beatrix M. G. Nielsen
Without any theory, machine learning has evolved a universal theory of data representation. Can we post-hoc rationalize it with math?
Boxes of numbers
Machine learning's universal theory of data representation
www.argmin.net
September 25, 2025 at 2:31 PM
Without any theory, machine learning has evolved a universal theory of data representation. Can we post-hoc rationalize it with math?
Reposted by Beatrix M. G. Nielsen
Congratulations to everyone who got their @neuripsconf.bsky.social papers accepted 🎉🎉🎉
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
September 19, 2025 at 9:13 AM
Congratulations to everyone who got their @neuripsconf.bsky.social papers accepted 🎉🎉🎉
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
Reposted by Beatrix M. G. Nielsen
- Fully funded PhD fellowship on Explainable NLU: apply by 31 October 2025, start in Spring 2026: candidate.hr-manager.net/ApplicationI...
- Open-topic PhD positions: express your interest through ELLIS by 31 October 2025, start in Autumn 2026: ellis.eu/news/ellis-p...
#NLProc #XAI
- Open-topic PhD positions: express your interest through ELLIS by 31 October 2025, start in Autumn 2026: ellis.eu/news/ellis-p...
#NLProc #XAI
PhD fellowship in Explainable Natural Language Understanding Department of Computer Science Faculty of SCIENCE University of Copenhagen
The Natural Language Processing Section at the Department of Computer Science, Faculty of Science at the University of Copenhagen invites applicants for a PhD f
candidate.hr-manager.net
September 1, 2025 at 2:20 PM
- Fully funded PhD fellowship on Explainable NLU: apply by 31 October 2025, start in Spring 2026: candidate.hr-manager.net/ApplicationI...
- Open-topic PhD positions: express your interest through ELLIS by 31 October 2025, start in Autumn 2026: ellis.eu/news/ellis-p...
#NLProc #XAI
- Open-topic PhD positions: express your interest through ELLIS by 31 October 2025, start in Autumn 2026: ellis.eu/news/ellis-p...
#NLProc #XAI
Reposted by Beatrix M. G. Nielsen
I wrote about the tragic death of Adam Raine and the venal negligence of "AI Safety." www.argmin.net/p/the-banal-...
The Banal Evil of AI Safety
Chatbot companies are harmful and dishonest. How can we hold them accountable?
www.argmin.net
August 28, 2025 at 2:30 PM
I wrote about the tragic death of Adam Raine and the venal negligence of "AI Safety." www.argmin.net/p/the-banal-...
Reposted by Beatrix M. G. Nielsen
🎓 Interested in a #PhD in machine learning or #AI? The ELLIS PhD Program connects top students with leading researchers across Europe. The application portal opens on Oct 1st. Curious? Join our info session on the same day. Get all the info 👉
ELLIS PhD Program: Call for Applications 2025
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI researchers. ELLIS also aims to boost economic growt...
ellis.eu
August 29, 2025 at 7:14 AM
Reposted by Beatrix M. G. Nielsen
I've been using Kagi for over a year as my default search engine. It's excellent.
"Paying for search changes the whole relationship between user, provider, search, and advertisers (the latter now being completely absent). It changes whom the provider is beholden to, their priorities, and ultimately search itself."
blog.optional.page/misc/kagi/
blog.optional.page/misc/kagi/
Why You Should Give Kagi A Try | Optional
A post by Optional
blog.optional.page
August 22, 2025 at 8:03 PM
I've been using Kagi for over a year as my default search engine. It's excellent.
Reposted by Beatrix M. G. Nielsen
Direct your research. Forge lifelong connections. Apply for the 2026 Complexity Postdoctoral Fellowships. SFI is looking for recent PhD graduates with quantitative and computational skills interested in theoretical collaborative research.
Deadline: Oct 1, 2025
Apply: santafe.edu/sfifellowship
Deadline: Oct 1, 2025
Apply: santafe.edu/sfifellowship
August 5, 2025 at 5:24 PM
Direct your research. Forge lifelong connections. Apply for the 2026 Complexity Postdoctoral Fellowships. SFI is looking for recent PhD graduates with quantitative and computational skills interested in theoretical collaborative research.
Deadline: Oct 1, 2025
Apply: santafe.edu/sfifellowship
Deadline: Oct 1, 2025
Apply: santafe.edu/sfifellowship
Reposted by Beatrix M. G. Nielsen
The EPFL NLP lab is looking to hire a postdoctoral researcher on the topic of designing, training, and evaluating multilingual LLMs:
docs.google.com/document/d/1...
Come join our dynamic group in beautiful Lausanne!
docs.google.com/document/d/1...
Come join our dynamic group in beautiful Lausanne!
EPFL NLP Postdoctoral Scholar Posting - Swiss AI LLMs
The EPFL Natural Language Processing (NLP) lab is looking to hire a postdoctoral researcher candidate in the area of multilingual LLM design, training, and evaluation. This postdoctoral position is as...
docs.google.com
August 4, 2025 at 3:54 PM
The EPFL NLP lab is looking to hire a postdoctoral researcher on the topic of designing, training, and evaluating multilingual LLMs:
docs.google.com/document/d/1...
Come join our dynamic group in beautiful Lausanne!
docs.google.com/document/d/1...
Come join our dynamic group in beautiful Lausanne!
Thank you to everyone who came to talk to us at ACL!
Very happy that so many people are interested in our work :D
If you didn’t manage to have a look yet: This work is relevant if you want to compare representations in language models, and it can be read here: arxiv.org/abs/2502.10201
Very happy that so many people are interested in our work :D
If you didn’t manage to have a look yet: This work is relevant if you want to compare representations in language models, and it can be read here: arxiv.org/abs/2502.10201
August 1, 2025 at 8:02 PM
Thank you to everyone who came to talk to us at ACL!
Very happy that so many people are interested in our work :D
If you didn’t manage to have a look yet: This work is relevant if you want to compare representations in language models, and it can be read here: arxiv.org/abs/2502.10201
Very happy that so many people are interested in our work :D
If you didn’t manage to have a look yet: This work is relevant if you want to compare representations in language models, and it can be read here: arxiv.org/abs/2502.10201
Reposted by Beatrix M. G. Nielsen
🏹 Job alert: Postdoc in Machine Learning (basic research) at @istaresearch.bsky.social in the group of Christoph Lampert (@mlcv-at-ista.bsky.social)
📍Klosterneuburg 🇦🇹
📅 Apply asap
🔗 More info: cvml.ista.ac.at/Postdoc-ML.h...
📍Klosterneuburg 🇦🇹
📅 Apply asap
🔗 More info: cvml.ista.ac.at/Postdoc-ML.h...
Machine Learning and Computer Vision Group -- Christoph Lampert -- ISTA
Computer Vision and Machine Learning, ISTA: open postdoc positions, Machine Learning, curiosity-driven, fully-funded
cvml.ista.ac.at
July 23, 2025 at 1:57 PM
🏹 Job alert: Postdoc in Machine Learning (basic research) at @istaresearch.bsky.social in the group of Christoph Lampert (@mlcv-at-ista.bsky.social)
📍Klosterneuburg 🇦🇹
📅 Apply asap
🔗 More info: cvml.ista.ac.at/Postdoc-ML.h...
📍Klosterneuburg 🇦🇹
📅 Apply asap
🔗 More info: cvml.ista.ac.at/Postdoc-ML.h...
Reposted by Beatrix M. G. Nielsen
Open PhD positions in Denmark! daracademy.dk/fellowship/f...
If you want to apply to work with me and Johannes Bjerva at @aau.dk Copenhagen, I'll be at @ic2s2.bsky.social this week and @aclmeeting.bsky.social next week! DM me if you'd like to meet :)
If you want to apply to work with me and Johannes Bjerva at @aau.dk Copenhagen, I'll be at @ic2s2.bsky.social this week and @aclmeeting.bsky.social next week! DM me if you'd like to meet :)
Dara
daracademy.dk
July 21, 2025 at 1:26 PM
Open PhD positions in Denmark! daracademy.dk/fellowship/f...
If you want to apply to work with me and Johannes Bjerva at @aau.dk Copenhagen, I'll be at @ic2s2.bsky.social this week and @aclmeeting.bsky.social next week! DM me if you'd like to meet :)
If you want to apply to work with me and Johannes Bjerva at @aau.dk Copenhagen, I'll be at @ic2s2.bsky.social this week and @aclmeeting.bsky.social next week! DM me if you'd like to meet :)
Reposted by Beatrix M. G. Nielsen
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 Beatrix M. G. Nielsen
1/
🚨 New paper at #ICML2025!
Identifying Latent Metric Structures in Deep Latent Variable Models 🎉
We solve part of the identifiability puzzle in generative models — using geometry. 🧵
🚨 New paper at #ICML2025!
Identifying Latent Metric Structures in Deep Latent Variable Models 🎉
We solve part of the identifiability puzzle in generative models — using geometry. 🧵
July 14, 2025 at 5:45 AM
1/
🚨 New paper at #ICML2025!
Identifying Latent Metric Structures in Deep Latent Variable Models 🎉
We solve part of the identifiability puzzle in generative models — using geometry. 🧵
🚨 New paper at #ICML2025!
Identifying Latent Metric Structures in Deep Latent Variable Models 🎉
We solve part of the identifiability puzzle in generative models — using geometry. 🧵
Our paper "Prediction Hubs are Context-Informed Frequent Tokens in LLMs" has been accepted at ACL 2025!
Main points:
1. Hubness is not a problem when language models do next-token prediction.
2. Nuisance hubness can appear when other comparisons are made.
Main points:
1. Hubness is not a problem when language models do next-token prediction.
2. Nuisance hubness can appear when other comparisons are made.
July 7, 2025 at 10:48 AM
Our paper "Prediction Hubs are Context-Informed Frequent Tokens in LLMs" has been accepted at ACL 2025!
Main points:
1. Hubness is not a problem when language models do next-token prediction.
2. Nuisance hubness can appear when other comparisons are made.
Main points:
1. Hubness is not a problem when language models do next-token prediction.
2. Nuisance hubness can appear when other comparisons are made.
Reposted by Beatrix M. G. Nielsen
📢 We are thrilled to introduce the ELLIS (@ellis.eu) x UniReps Speaker Series!📢
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
April 1, 2025 at 3:48 PM
📢 We are thrilled to introduce the ELLIS (@ellis.eu) x UniReps Speaker Series!📢
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
🔵🔴 Each monthly session features a 40-min Keynote talk and a 20min-Flash talk.
📜 You can nominate yourself or another researcher as a speaker by filling out the nomination form: forms.gle/EbHatQW7zoVi...
Reposted by Beatrix M. G. Nielsen
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
NeurIPS participation in Europe
We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...
docs.google.com
March 30, 2025 at 6:04 PM
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)