Janis Keuper 🇮🇱
@janiskeuper.bsky.social
Pinned
Janis Keuper 🇮🇱
@janiskeuper.bsky.social
· Jun 14
Presenting our poster #45 today at #CVPR in poster session 3: "PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?"
cvpr.thecvf.com/virtual/2025...
cvpr.thecvf.com/virtual/2025...
Reposted by Janis Keuper 🇮🇱
A small step for science, quite a big one for us: reaching 10k citations. Thanks to all co-authors! scholar.google.de/citations?hl...
November 15, 2025 at 8:24 PM
A small step for science, quite a big one for us: reaching 10k citations. Thanks to all co-authors! scholar.google.de/citations?hl...
Reposted by Janis Keuper 🇮🇱
blog.arxiv.org/2025/10/31/a...
FYI the blog post for the updated policy is out. Our llm future is dire:/
FYI the blog post for the updated policy is out. Our llm future is dire:/
October 31, 2025 at 7:37 PM
blog.arxiv.org/2025/10/31/a...
FYI the blog post for the updated policy is out. Our llm future is dire:/
FYI the blog post for the updated policy is out. Our llm future is dire:/
Looks like I belong to the big boys now 🫡
Mail from OpenAI: "Congratulations on processing over 10 billion tokens with the OpenAI API." 😅
A lot of these tokens went into this project:
"Prompt Injection Attacks on LLM Generated
Reviews of Scientific Publications"
arxiv.org/pdf/2509.10248
Mail from OpenAI: "Congratulations on processing over 10 billion tokens with the OpenAI API." 😅
A lot of these tokens went into this project:
"Prompt Injection Attacks on LLM Generated
Reviews of Scientific Publications"
arxiv.org/pdf/2509.10248
arxiv.org
October 9, 2025 at 7:54 AM
Looks like I belong to the big boys now 🫡
Mail from OpenAI: "Congratulations on processing over 10 billion tokens with the OpenAI API." 😅
A lot of these tokens went into this project:
"Prompt Injection Attacks on LLM Generated
Reviews of Scientific Publications"
arxiv.org/pdf/2509.10248
Mail from OpenAI: "Congratulations on processing over 10 billion tokens with the OpenAI API." 😅
A lot of these tokens went into this project:
"Prompt Injection Attacks on LLM Generated
Reviews of Scientific Publications"
arxiv.org/pdf/2509.10248
Our new paper (accepted at #NeurIPS UrbanAI Workshop): "Real-time Prediction of Urban Sound Propagation
with Conditioned Normalizing Flows" arxiv.org/pdf/2510.04510 is part of our work using generative model to predict complex physics www.physics-gen.org
with Conditioned Normalizing Flows" arxiv.org/pdf/2510.04510 is part of our work using generative model to predict complex physics www.physics-gen.org
October 9, 2025 at 7:22 AM
Our new paper (accepted at #NeurIPS UrbanAI Workshop): "Real-time Prediction of Urban Sound Propagation
with Conditioned Normalizing Flows" arxiv.org/pdf/2510.04510 is part of our work using generative model to predict complex physics www.physics-gen.org
with Conditioned Normalizing Flows" arxiv.org/pdf/2510.04510 is part of our work using generative model to predict complex physics www.physics-gen.org
Our GCPR @gcpr-by-dagm.bsky.social paper (Oral) "Assessing Foundation Models for Mold Colony Detection with Limited Training Data" is now on Arxiv: arxiv.org/pdf/2510.00561
October 2, 2025 at 12:58 PM
Our GCPR @gcpr-by-dagm.bsky.social paper (Oral) "Assessing Foundation Models for Mold Colony Detection with Limited Training Data" is now on Arxiv: arxiv.org/pdf/2510.00561
Reposted by Janis Keuper 🇮🇱
Our #NeurIPS ORAL "MaxSup: Overcoming Representation Collapse in Label Smoothing", joint work with @cispa.de, is now on Arxiv: arxiv.org/pdf/2502.15798
October 2, 2025 at 11:58 AM
Our #NeurIPS ORAL "MaxSup: Overcoming Representation Collapse in Label Smoothing", joint work with @cispa.de, is now on Arxiv: arxiv.org/pdf/2502.15798
Following up on the discussions about prompt injections which were found in Arxiv paper sources - indicating that some authors try to manipulate LLM generate reviews: beyond the ethical implications, I was wondering if this actually works and did some experiments...
arxiv.org/abs/2509.10248
arxiv.org/abs/2509.10248
Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications
The ongoing intense discussion on rising LLM usage in the scientific peer-review process has recently been mingled by reports of authors using hidden prompt injections to manipulate review scores. Sin...
arxiv.org
September 16, 2025 at 7:51 AM
Following up on the discussions about prompt injections which were found in Arxiv paper sources - indicating that some authors try to manipulate LLM generate reviews: beyond the ethical implications, I was wondering if this actually works and did some experiments...
arxiv.org/abs/2509.10248
arxiv.org/abs/2509.10248
Reposted by Janis Keuper 🇮🇱
Very glad to see that someone is doing the important work of aligning AI alignment. alignmentalignment.ai
Center for the Alignment of AI Alignment Centers
We align the aligners
alignmentalignment.ai
September 11, 2025 at 1:04 PM
Very glad to see that someone is doing the important work of aligning AI alignment. alignmentalignment.ai
Reposted by Janis Keuper 🇮🇱
MIT’s NANDA initiative found that 95% of generative AI deployments fail after interviewing 150 execs, surveying 350 workers, and analyzing 300 projects. The real “productivity gains” seem to come from layoffs and squeezing more work from fewer people not AI.
MIT report: 95% of generative AI pilots at companies are failing
There’s a stark difference in success rates between companies that purchase AI tools from vendors and those that build them internally.
fortune.com
August 20, 2025 at 4:52 AM
MIT’s NANDA initiative found that 95% of generative AI deployments fail after interviewing 150 execs, surveying 350 workers, and analyzing 300 projects. The real “productivity gains” seem to come from layoffs and squeezing more work from fewer people not AI.
Reposted by Janis Keuper 🇮🇱
Update on hidden prompts in papers targeting LLM reviews: ICML 2025 PCs react.
icml.cc/Conferences/...
icml.cc/Conferences/...
July 23, 2025 at 12:07 PM
Update on hidden prompts in papers targeting LLM reviews: ICML 2025 PCs react.
icml.cc/Conferences/...
icml.cc/Conferences/...
Reposted by Janis Keuper 🇮🇱
![4-panel comic. (1) [Person 1 with ponytail flanked by person with short hair and another person speaking into microphone at podium] PERSON 1: In the early 2010s, researchers found that many major scientific results couldn’t be reproduced. (2) PERSON 1: Over a decade into the replication crisis, we wanted to see if today’s studies have become more robust. (3) PERSON 1: Unfortunately, our replication analysis has found exactly the same problems that those 2010s researchers did. (4) [newspaper with image of speakers from previous panels] Headline: Replication Crisis Solved](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:cz73r7iyiqn26upot4jtjdhk/bafkreibwuu57ullc7vacjyno6c5z3gtyakkg2qub6cn3dbbjdpn2kaowmi@jpeg)
July 21, 2025 at 11:54 PM
Reposted by Janis Keuper 🇮🇱
🚀 Calling all ML, CV and Sensor Enthusiasts!
Join us at the L2S: Learning to Sense Workshop at #NeurIPS2025 !
🗓 Date: December 6/7, 2025
📍 Location: San Diego, USA
sites.google.com/view/l2s-wor...
Join us at the L2S: Learning to Sense Workshop at #NeurIPS2025 !
🗓 Date: December 6/7, 2025
📍 Location: San Diego, USA
sites.google.com/view/l2s-wor...
July 22, 2025 at 11:54 AM
🚀 Calling all ML, CV and Sensor Enthusiasts!
Join us at the L2S: Learning to Sense Workshop at #NeurIPS2025 !
🗓 Date: December 6/7, 2025
📍 Location: San Diego, USA
sites.google.com/view/l2s-wor...
Join us at the L2S: Learning to Sense Workshop at #NeurIPS2025 !
🗓 Date: December 6/7, 2025
📍 Location: San Diego, USA
sites.google.com/view/l2s-wor...
Reposted by Janis Keuper 🇮🇱
Attending #ICML2025? Watch out for our paper "DCBM: Data-Efficient Visual Concept Bottleneck Models" presented by @katharinaprasse.bsky.social -> github.com/KathPra/DCBM
July 15, 2025 at 6:42 AM
Attending #ICML2025? Watch out for our paper "DCBM: Data-Efficient Visual Concept Bottleneck Models" presented by @katharinaprasse.bsky.social -> github.com/KathPra/DCBM
Reposted by Janis Keuper 🇮🇱
Congratulations to @paulgavrikov.bsky.social for an excellent PhD defense today!
July 8, 2025 at 7:02 PM
Congratulations to @paulgavrikov.bsky.social for an excellent PhD defense today!
Reposted by Janis Keuper 🇮🇱
Two papers with @keuper-labs.bsky.social participation accepted at #ICCV2025:
1) Scientific figure generation with TikZero, it generates scientific figures from text as high-level, human-interpretable, and editable graphics programs -> arxiv.org/pdf/2503.11509
1) Scientific figure generation with TikZero, it generates scientific figures from text as high-level, human-interpretable, and editable graphics programs -> arxiv.org/pdf/2503.11509
June 30, 2025 at 8:14 AM
Two papers with @keuper-labs.bsky.social participation accepted at #ICCV2025:
1) Scientific figure generation with TikZero, it generates scientific figures from text as high-level, human-interpretable, and editable graphics programs -> arxiv.org/pdf/2503.11509
1) Scientific figure generation with TikZero, it generates scientific figures from text as high-level, human-interpretable, and editable graphics programs -> arxiv.org/pdf/2503.11509
Searching for latex symbols? I found this handy tool: detexify.kirelabs.org/classify.html
June 23, 2025 at 9:05 AM
Searching for latex symbols? I found this handy tool: detexify.kirelabs.org/classify.html
Reposted by Janis Keuper 🇮🇱
🚨 Calling all Vision and ML researchers! 🚨
Missed the regular GCPR deadline?
No worries, the Fast Review Track deadline is July 1, 2025 (11:59 PM CEST).
Polish up that revision from a previous submission and submit now! 🔄✍️
#GCPR2025 #ComputerVision #AIResearch
Missed the regular GCPR deadline?
No worries, the Fast Review Track deadline is July 1, 2025 (11:59 PM CEST).
Polish up that revision from a previous submission and submit now! 🔄✍️
#GCPR2025 #ComputerVision #AIResearch
June 21, 2025 at 12:19 PM
🚨 Calling all Vision and ML researchers! 🚨
Missed the regular GCPR deadline?
No worries, the Fast Review Track deadline is July 1, 2025 (11:59 PM CEST).
Polish up that revision from a previous submission and submit now! 🔄✍️
#GCPR2025 #ComputerVision #AIResearch
Missed the regular GCPR deadline?
No worries, the Fast Review Track deadline is July 1, 2025 (11:59 PM CEST).
Polish up that revision from a previous submission and submit now! 🔄✍️
#GCPR2025 #ComputerVision #AIResearch
Presenting our poster #45 today at #CVPR in poster session 3: "PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?"
cvpr.thecvf.com/virtual/2025...
cvpr.thecvf.com/virtual/2025...
June 14, 2025 at 11:19 AM
Presenting our poster #45 today at #CVPR in poster session 3: "PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?"
cvpr.thecvf.com/virtual/2025...
cvpr.thecvf.com/virtual/2025...
Reposted by Janis Keuper 🇮🇱
A Visual RAG Pipeline for Few-Shot Fine-Grained Product Classification
@bianca-lamm.bsky.social @janiskeuper.bsky.social
Poster Wed. 2-4pm at ExHall D
Fine-Grained Visual Categorization Workshop at #CVPR2025 (
sites.google.com/view/fgvc12)
arxiv.org/pdf/2504.11838?
@bianca-lamm.bsky.social @janiskeuper.bsky.social
Poster Wed. 2-4pm at ExHall D
Fine-Grained Visual Categorization Workshop at #CVPR2025 (
sites.google.com/view/fgvc12)
arxiv.org/pdf/2504.11838?
June 11, 2025 at 10:10 AM
A Visual RAG Pipeline for Few-Shot Fine-Grained Product Classification
@bianca-lamm.bsky.social @janiskeuper.bsky.social
Poster Wed. 2-4pm at ExHall D
Fine-Grained Visual Categorization Workshop at #CVPR2025 (
sites.google.com/view/fgvc12)
arxiv.org/pdf/2504.11838?
@bianca-lamm.bsky.social @janiskeuper.bsky.social
Poster Wed. 2-4pm at ExHall D
Fine-Grained Visual Categorization Workshop at #CVPR2025 (
sites.google.com/view/fgvc12)
arxiv.org/pdf/2504.11838?
Reposted by Janis Keuper 🇮🇱
Main #CVPR2025 Conference Paper:
PhysicsGen - Can Generative Models Learn from Images to Predict Complex Physical Relations?
Martin Spitznagel, Jan Vailant, @janiskeuper.bsky.social
Sat 14 Jun 10:30 a.m. CDT — 12:30 p.m. ExHall D Poster #45
cvpr.thecvf.com/virtual/2025...
PhysicsGen - Can Generative Models Learn from Images to Predict Complex Physical Relations?
Martin Spitznagel, Jan Vailant, @janiskeuper.bsky.social
Sat 14 Jun 10:30 a.m. CDT — 12:30 p.m. ExHall D Poster #45
cvpr.thecvf.com/virtual/2025...
June 11, 2025 at 10:02 AM
Main #CVPR2025 Conference Paper:
PhysicsGen - Can Generative Models Learn from Images to Predict Complex Physical Relations?
Martin Spitznagel, Jan Vailant, @janiskeuper.bsky.social
Sat 14 Jun 10:30 a.m. CDT — 12:30 p.m. ExHall D Poster #45
cvpr.thecvf.com/virtual/2025...
PhysicsGen - Can Generative Models Learn from Images to Predict Complex Physical Relations?
Martin Spitznagel, Jan Vailant, @janiskeuper.bsky.social
Sat 14 Jun 10:30 a.m. CDT — 12:30 p.m. ExHall D Poster #45
cvpr.thecvf.com/virtual/2025...
Reposted by Janis Keuper 🇮🇱
We are presenting 7 papers (main conference+ workshops) at #CVPR2025 www.keuper-labs.org/research/?se...
June 11, 2025 at 9:55 AM
We are presenting 7 papers (main conference+ workshops) at #CVPR2025 www.keuper-labs.org/research/?se...
Reposted by Janis Keuper 🇮🇱
🚀 Exciting news! #GCPR2025 – the DAGM German Conference on Pattern Recognition – is coming to Freiburg, Germany! 📍🗓️ Mark your calendars: September 23-26, 2025!
May 8, 2025 at 9:49 PM
🚀 Exciting news! #GCPR2025 – the DAGM German Conference on Pattern Recognition – is coming to Freiburg, Germany! 📍🗓️ Mark your calendars: September 23-26, 2025!
Reposted by Janis Keuper 🇮🇱
I asked "on the other platform" what were the most important improvements to the original 2017 transformer.
That was quite popular and here is a synthesis of the responses:
That was quite popular and here is a synthesis of the responses:
April 28, 2025 at 6:47 AM
I asked "on the other platform" what were the most important improvements to the original 2017 transformer.
That was quite popular and here is a synthesis of the responses:
That was quite popular and here is a synthesis of the responses:
Reposted by Janis Keuper 🇮🇱
Visit our poster presentations at #ICLR2025 iclr.cc/virtual/2025...
April 22, 2025 at 7:57 AM
Visit our poster presentations at #ICLR2025 iclr.cc/virtual/2025...
Reposted by Janis Keuper 🇮🇱
On Thursday, I'll be presenting our paper "Can We Talk Models Into Seeing the World Differently?" (#328) at ICLR 2025 in Singapore! If you're attending or just around Singapore, l'd love to connect—feel free to reach out! Also, I’m exploring postdoc or industry opportunities–happy to chat!
April 21, 2025 at 10:47 AM
On Thursday, I'll be presenting our paper "Can We Talk Models Into Seeing the World Differently?" (#328) at ICLR 2025 in Singapore! If you're attending or just around Singapore, l'd love to connect—feel free to reach out! Also, I’m exploring postdoc or industry opportunities–happy to chat!