Sign in

Stella Frank

@scfrank.bsky.social
134 followers 403 following 19 posts

Thinking about multimodal representations | Postdoc at UCPH/Pioneer Centre for AI (DK).

PostsRepliesMedia
Reposted by Stella Frank
Neehar Kondapaneni @therealpaneni.bsky.social · 19/11/2025
Excited to share our paper Representational Difference Explanations (RDX) was accepted to #NeurIPS2025! 🎉RDX is a new method for model diffing designed to isolate 🔍 representational differences. 1/7
184
Reposted by Stella Frank
Christoph Heilig @christophheilig.bsky.social · 26/08/2025
1/8 🧵 GPT-5's storytelling problems reveal a deeper AI safety issue. I've been testing its creative writing capabilities, and the results are concerning - not just for literature, but for AI development more broadly. 🚨
36126
Reposted by Stella Frank
Bonan Zhao (赵博囡) @bonan.bsky.social · 17/08/2025
My Lab at the University of Edinburgh🇬🇧 has funded PhD positions for this cycle! We study the computational principles of how people learn, reason, and communicate. It's a new lab, and you will be playing a big role in shaping its culture and foundations. Spread the words!
25721
Reposted by Stella Frank
Nicolas Dufour @nicolasdufour.bsky.social · 18/08/2025
🚀 DinoV3 just became the new go-to backbone for geoloc! It outperforms CLIP-like models (SigLip2, finetuned StreetCLIP)… and that’s shocking 🤯 Why? CLIP models have an innate advantage — they literally learn place names + images. DinoV3 doesn’t.
14614
Reposted by Stella Frank
halvarflake.bsky.social @halvarflake.bsky.social · 07/07/2025
I wrote a short rant about what irks me when people anthropomorphize LLMs: addxorrol.blogspot.com/2025/07/a-no...
addxorrol.blogspot.com
A non-anthropomorphized view of LLMs
In many discussions where questions of "alignment" or "AI safety" crop up, I am baffled by seriously intelligent people imbuing almost magic...
53714
Reposted by Stella Frank
Desmond Elliott @delliott.bsky.social · 07/07/2025
📢I am hiring a Postdoc to work on post-training methods for low-resource languages. Apply by August 15 employment.ku.dk/faculty/?sho.... Let's talk at #ACL2025NLP in Vienna if you want to know more about the position and life in Denmark.
employment.ku.dk
Postdoc in Natural Language Processing
02312
Reposted by Stella Frank
Dr Abeba Birhane @abeba.blacksky.app · 25/06/2025
New paper hot off the press www.nature.com/articles/s41... We analysed over 40,000 computer vision papers from CVPR (the longest standing CV conf) & associated patents tracing pathways from research to application. We found that 90% of papers & 86% of downstream patents power surveillance 1/
nature.com
Computer-vision research powers surveillance technology - Nature
An analysis of research papers and citing patents indicates the extensive ties between computer-vision research and surveillance.
341010554
Reposted by Stella Frank
Liesbeth Corens @onslies.bsky.social · 15/06/2025
"Researching and reflecting on the harms of AI is not itself harm reduction. It may even contribute to rationalizing, normalizing, and enabling harm. Critical reflection without appropriate action is thus quintessentially critical washing."
03714
Stella Frank @scfrank.bsky.social · 17/06/2025
Fallacy of the Day: Calling two different things by the same name doesn't make them the same (jingle) and calling the same thing by different names doesn't make them different (jangle) en.wikipedia.org/wiki/Jingle-... (this is going to be so useful for reviewing)
en.wikipedia.org
Jingle-jangle fallacies - Wikipedia
000
Stella Frank @scfrank.bsky.social · 13/06/2025
📯 Best Paper Award at CVPR workshop on Visual concepts for our (@doneata.bsky.social + @delliott.bsky.social) paper on probing vision/lang/ vision+lang models for semantic norms! TLDR: SSL vision models (swinV2, dinoV2) are surprisingly similar to LLM & VLMs even w/o lang 👀 arxiv.org/abs/2506.03994
1134
Reposted by Stella Frank
Srishti @srishtiy.bsky.social · 02/06/2025
I am excited to announce our latest work 🎉 "Cultural Evaluations of Vision-Language Models Have a Lot to Learn from Cultural Theory". We review recent works on culture in VLMs and argue for deeper grounding in cultural theory to enable more inclusive evaluations. Paper 🔗: arxiv.org/pdf/2505.22793
Paper title "Cultural Evaluations of Vision-Language Models
Have a Lot to Learn from Cultural Theory"
35818
Reposted by Stella Frank
Maria Antoniak @mariaa.bsky.social · 02/06/2025
Check out our new paper led by @srishtiy.bsky.social and @nolauren.bsky.social! This work brings together computer vision, cultural theory, semiotics, and visual studies to provide new tools and perspectives for the study of ~culture~ in VLMs.
1268
Reposted by Stella Frank
kyunghyuncho.bsky.social @kyunghyuncho.bsky.social · 20/05/2025
as an extra take-away, this implies that our eval tends to be overly precision focused. we should really think of what we lose in terms of recalls, as this directly relates to what we miss out for whom when we build these large-scale, general-purpose models. (4/4)
142
Reposted by Stella Frank
Cohere Labs @cohereforai.bsky.social · 10/04/2025
🚀 We are excited to introduce Kaleidoscope, the largest culturally-authentic exam benchmark. 📌 Most VLM benchmarks are English-centric or rely on translations—missing linguistic & cultural nuance. Kaleidoscope expands in-language multilingual 🌎 & multimodal 👀 VLMs evaluation
1197
Reposted by Stella Frank
Lazaros Nalpantidis @lanalpa.bsky.social · 11/04/2025
Join us and revolutionize Life Science Lab Automation! 🎓🤖💉 I am hiring a Postdoc in Robotics and Computer Vision for Life Science Laboratory Automation, in Copenhagen, Denmark. Is that you? 🙋‍♀️ efzu.fa.em2.oraclecloud.com/hcmUI/Candid...
efzu.fa.em2.oraclecloud.com
Postdoc in Robotics and Computer Vision for Life Science Laboratory Automation - DTU Electro
As part of a joint research collaboration between DTU and Novo Nordisk, we are looking for a postdoc to join our multidisciplinary research program focusing on the interplay between AI-Protein design,...
093
Reposted by Stella Frank
Isra Salazar @israsalazar.bsky.social · 10/04/2025
Today we are releasing Kaleidoscope 🎉 A comprehensive multimodal & multilingual benchmark for VLMs! It contains real questions from exams in different languages. 🌍 20,911 questions and 18 languages 📚 14 subjects (STEM → Humanities) 📸 55% multimodal questions
1266
Reposted by Stella Frank
Marcel Binz @marcelbinz.bsky.social · 09/04/2025
We are looking for two PhD students at our institute in Munich. Both postions are open-topic, so anything between cognitive science and machine learning is possible. More information: hcai-munich.com/PhDHCAI.pdf Feel free to share broadly!
hcai-munich.com
165
Reposted by Stella Frank
MAPS - CVPR 2026 Workshop @mapscvpr.bsky.social · 14/03/2025
📢Excited to announce our upcoming workshop - Vision Language Models For All: Building Geo-Diverse and Culturally Aware Vision-Language Models (VLMs-4-All) @CVPR 2025! 🌐 sites.google.com/view/vlms4all
11711
Reposted by Stella Frank
FGVC Workshop @fgvcworkshop.bsky.social · 09/04/2025
BirdCLEF25: Audio-based species identification focused on birds, amphibians, mammals, and insects in Colombia. 👉 www.kaggle.com/competitions... @cvprconference.bsky.social @kaggle.com #FGVC #CVPR #CVPR2025 #LifeCLEF [1/4]
1911
Reposted by Stella Frank
Auke-Florian 🪹 @aukeflorian.nl · 09/04/2025
Thanks to these insects, we can now study environmental microplastics retrospectively. 🔍 Even before Duprat began his now famous experiments with caddisfly larvae, insects in the wild were already experimenting with plastic... 🐛 14/x
Above: Casing of Ironoquia dubia (RMNH.INS.1544419) collected on May 18th 1971 in Loenen, The Netherlands. b) The label of the specimen.  Depicted on the right: detail of the artificial items.  Photographs: overview: Auke-Florian Hiemstra, details: Pasquale Ciliberti. Below: Caddisfly larvae in the studio of Hubert Duprat, carrying cases made from mostly gold. © Hubert Duprat, adagp, 2024, Courtesy the Artist and Art : Concept, Paris, Photo F. Delpech.
11408
Stella Frank @scfrank.bsky.social · 06/04/2025
What a weekend to find Heinrich von Kleist's Erzählungen next to the skip, in which the first story is literally about a man wreaking murderous havoc because of the imposition of arbitrary trade tariffs en.wikipedia.org/wiki/Michael...
020
Reposted by Stella Frank
Mike Williams @mwilli.bsky.social · 05/04/2025
Portland, ME showed up. #HandsOff
241198083944
Reposted by Stella Frank
Bloomberg News @bloomberg.com · 03/04/2025
The world's 500 richest people saw their combined wealth fall by a combined $208 billion, the most since Covid, as tariffs sent markets into a tailspin
bloomberg.com
Billionaires Lose Combined $208 Billion in One Day From Trump Tariffs
The world’s 500 richest people saw their combined wealth plunge by $208 billion Thursday as broad tariffs announced by President Donald Trump sent global markets into a tailspin.
134605110
Reposted by Stella Frank
Neil Cohn @neilcohn.bsky.social · 04/04/2025
I’m excited to share our newest paper which is the first to analyze all of our in our TINTIN Corpus: 1,030 comics from 144 countries. We asked: How much are comic layouts influenced by the writing systems of their authors? www.sciencedirect.com/science/arti...
Comic page layouts and their directionsMap depicting how many comics in the TINTIN Corpus come from different countries, along with how many styles per region of the world
23511
Reposted by Stella Frank
Comfortably Numb @numb.comfortab.ly · 30/03/2025
www.pcgamer.com/games/advent...
pcgamer.com
Get up to 85% off some of the PCs weirdest adventure games, all to benefit 'humanitarian relief in Ukraine'
The Amanita for Ukraine deal runs until April 2.
14715
Reposted by Stella Frank
Serge Belongie @serge.belongie.com · 30/03/2025
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)
docs.google.com
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 ...
6279161
Stella Frank @scfrank.bsky.social · 28/03/2025
Beautiful and motivated use of generated imagery 💙 wattenberger.com/thoughts/our... by @wattenberger.com More of this kind of thing please!
wattenberger.com
Our interfaces have lost their senses
110
Reposted by Stella Frank
Laura White @laurakwhite.bsky.social · 26/03/2025
Does anyone have a nice guide to digital privacy aimed at non-citizen residents traveling & returning to the US? I've been trying to check in with scientists I know with upcoming travel and am realizing many folks could use a 101 on removing biometric unlocking, doing a fresh iOS install, etc.
1910917
Stella Frank @scfrank.bsky.social · 21/03/2025
Explains what's happening at the border: while you're in the air, the CBP is trawling state and federal databases to find that one time you got pulled over ten years ago. Advance Passenger Information Systems tells them who's coming.
030
Reposted by Stella Frank
Nancy Kanwisher @nancykanwisher.bsky.social · 20/03/2025
Here are six examples of how foreign visitors to the US with no criminal record are being treated: 1. Mahmoud Khalil, a green card holding student with no criminal record married to an American is abducted by ICE and is still in detention over a week later. www.nytimes.com/2025/03/19/n... ......
37545
Stella Frank @scfrank.bsky.social · 01/03/2025
Inspired by languagelog.ldc.upenn.edu/nll/?p=68451 , I asked Claude for elephant-free rooms and honestly got much more than I expected
Empty room with very small elephants that barely count. GPT asks "Would you like me to try again with an even more elephant-free approach?"
131