Paul Hager
@paulhager.bsky.social
PhD student interested in benchmarking medical LLMs and understanding how to best use tabular data in deep learning.
Reposted by Paul Hager
Quick look back at an insightful day yesterday at the Bavarian Conference on AI in Medicine, where @paulhager.bsky.social , @luciehuang.bsky.social, Alina Dima, and Vasiliki Sideri-Lampretsa were representing us.
Team, thank you for being such good ambassadors! 👏
#AIMNews #AIinMedicine
Team, thank you for being such good ambassadors! 👏
#AIMNews #AIinMedicine
October 29, 2025 at 12:23 PM
Quick look back at an insightful day yesterday at the Bavarian Conference on AI in Medicine, where @paulhager.bsky.social , @luciehuang.bsky.social, Alina Dima, and Vasiliki Sideri-Lampretsa were representing us.
Team, thank you for being such good ambassadors! 👏
#AIMNews #AIinMedicine
Team, thank you for being such good ambassadors! 👏
#AIMNews #AIinMedicine
Reposted by Paul Hager
1. Social media is now 5% following friends and 95% watching videos made by strangers.
2. Every podcast is turning into a YouTube show.
3. AI companies can't stop building TikTok clones.
Everything is becoming television.
I wrote about why that matters.
www.derekthompson.org/p/why-everyt...
2. Every podcast is turning into a YouTube show.
3. AI companies can't stop building TikTok clones.
Everything is becoming television.
I wrote about why that matters.
www.derekthompson.org/p/why-everyt...
Everything Is Television
A theory of culture and attention
www.derekthompson.org
October 10, 2025 at 12:24 PM
1. Social media is now 5% following friends and 95% watching videos made by strangers.
2. Every podcast is turning into a YouTube show.
3. AI companies can't stop building TikTok clones.
Everything is becoming television.
I wrote about why that matters.
www.derekthompson.org/p/why-everyt...
2. Every podcast is turning into a YouTube show.
3. AI companies can't stop building TikTok clones.
Everything is becoming television.
I wrote about why that matters.
www.derekthompson.org/p/why-everyt...
Commuting in cities without headphones make you feel more like you're part of society and not just on your own lonely island. Much nicer than the 1000th podcast or song
October 10, 2025 at 1:40 PM
Commuting in cities without headphones make you feel more like you're part of society and not just on your own lonely island. Much nicer than the 1000th podcast or song
The speed at which LLMs allow you to try new research ideas is astounding. Especially for the sweet spot where the logic is not fantastically complex but the implementation is laborious.
October 10, 2025 at 1:39 PM
The speed at which LLMs allow you to try new research ideas is astounding. Especially for the sweet spot where the logic is not fantastically complex but the implementation is laborious.
Reposted by Paul Hager
Submit to our @euripsconf.bsky.social workshop :
MedEurIPS - Medical Imaging meets EurIPS
sites.google.com/view/medeurips
@aasaferagen.bsky.social
@benglocker.bsky.social @bernhardkainz.bsky.social
@danielrueckert.bsky.social
Ender Konukoglu
@stsaftaris.bsky.social
MedEurIPS - Medical Imaging meets EurIPS
sites.google.com/view/medeurips
@aasaferagen.bsky.social
@benglocker.bsky.social @bernhardkainz.bsky.social
@danielrueckert.bsky.social
Ender Konukoglu
@stsaftaris.bsky.social
MedEurIPS
HOME
sites.google.com
October 1, 2025 at 1:57 PM
Submit to our @euripsconf.bsky.social workshop :
MedEurIPS - Medical Imaging meets EurIPS
sites.google.com/view/medeurips
@aasaferagen.bsky.social
@benglocker.bsky.social @bernhardkainz.bsky.social
@danielrueckert.bsky.social
Ender Konukoglu
@stsaftaris.bsky.social
MedEurIPS - Medical Imaging meets EurIPS
sites.google.com/view/medeurips
@aasaferagen.bsky.social
@benglocker.bsky.social @bernhardkainz.bsky.social
@danielrueckert.bsky.social
Ender Konukoglu
@stsaftaris.bsky.social
Few things as satisfying as the moment when your paper finally is within the page limit after hours of rewriting, figure optimizations, and moving things to the appendix.
September 23, 2025 at 10:31 PM
Few things as satisfying as the moment when your paper finally is within the page limit after hours of rewriting, figure optimizations, and moving things to the appendix.
Reposted by Paul Hager
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 Paul Hager
And lastly, if @neuripsconf.bsky.social would choose to reverse the decisions on the papers affected by space constraints, we would be happy and able to accommodate their presentation
September 19, 2025 at 10:01 AM
And lastly, if @neuripsconf.bsky.social would choose to reverse the decisions on the papers affected by space constraints, we would be happy and able to accommodate their presentation
The policy of rejecting accepted papers by NeurIPs due to "space issues" will affect so many conferences going forward that now need to also deal with papers that should have already been published competing with new research. These conferences have structural issues that must be fixed.
September 19, 2025 at 2:53 PM
The policy of rejecting accepted papers by NeurIPs due to "space issues" will affect so many conferences going forward that now need to also deal with papers that should have already been published competing with new research. These conferences have structural issues that must be fixed.
People who try to start „crowd clapping on beat“ at live music performances should be thrown in jail
August 29, 2025 at 6:59 AM
People who try to start „crowd clapping on beat“ at live music performances should be thrown in jail
Reposted by Paul Hager
🚀 Towards cardiac MRI foundation models:
Comprehensive visual-tabular representations for whole-heart assessment and beyond.
We introduce ViTa, a multi-view, multi-modal, multi-task model for cardiac MRI.
🧵 1/3
Comprehensive visual-tabular representations for whole-heart assessment and beyond.
We introduce ViTa, a multi-view, multi-modal, multi-task model for cardiac MRI.
🧵 1/3
August 26, 2025 at 3:57 PM
🚀 Towards cardiac MRI foundation models:
Comprehensive visual-tabular representations for whole-heart assessment and beyond.
We introduce ViTa, a multi-view, multi-modal, multi-task model for cardiac MRI.
🧵 1/3
Comprehensive visual-tabular representations for whole-heart assessment and beyond.
We introduce ViTa, a multi-view, multi-modal, multi-task model for cardiac MRI.
🧵 1/3
Reposted by Paul Hager
🔃 We're moving beyond traditional benchmarking for LLMs.
🚩 Meet Dynamic, Automatic & Systematic (DAS) Red-Teaming from Jiazhen Pan and Bailiang Jian together with great collaborators! #AIMresearch
🧵 1/4
🚩 Meet Dynamic, Automatic & Systematic (DAS) Red-Teaming from Jiazhen Pan and Bailiang Jian together with great collaborators! #AIMresearch
🧵 1/4
August 20, 2025 at 12:39 PM
🔃 We're moving beyond traditional benchmarking for LLMs.
🚩 Meet Dynamic, Automatic & Systematic (DAS) Red-Teaming from Jiazhen Pan and Bailiang Jian together with great collaborators! #AIMresearch
🧵 1/4
🚩 Meet Dynamic, Automatic & Systematic (DAS) Red-Teaming from Jiazhen Pan and Bailiang Jian together with great collaborators! #AIMresearch
🧵 1/4
Hold on a second, summer hasn’t even begun. Three weeks of rain and 18 degrees does not a summer make.
August 1, 2025 at 10:38 AM
Hold on a second, summer hasn’t even begun. Three weeks of rain and 18 degrees does not a summer make.
So after spending a couple of days at CVPR I always get really hype about how far CV has come and then I ask 4o and Imagen to generate a map with 4 pins in it and I'm quickly thrown back to reality
June 24, 2025 at 3:26 PM
So after spending a couple of days at CVPR I always get really hype about how far CV has come and then I ask 4o and Imagen to generate a map with 4 pins in it and I'm quickly thrown back to reality
I will never get used to how cold American buildings are. I love it when it’s over 30 degrees outside and then less than 15 inside. So much fun being permanently too cold or too hot.
June 12, 2025 at 10:09 PM
I will never get used to how cold American buildings are. I love it when it’s over 30 degrees outside and then less than 15 inside. So much fun being permanently too cold or too hot.
The ideal modern AI research workflow is:
1. Develop a new benchmark to show a weakness of SOTA models.
2. Create a new (or cleverly adapt an old) dataset to address this weakness.
3. Retrain a transformer.
1. Develop a new benchmark to show a weakness of SOTA models.
2. Create a new (or cleverly adapt an old) dataset to address this weakness.
3. Retrain a transformer.
June 12, 2025 at 10:06 PM
The ideal modern AI research workflow is:
1. Develop a new benchmark to show a weakness of SOTA models.
2. Create a new (or cleverly adapt an old) dataset to address this weakness.
3. Retrain a transformer.
1. Develop a new benchmark to show a weakness of SOTA models.
2. Create a new (or cleverly adapt an old) dataset to address this weakness.
3. Retrain a transformer.
Biggest takeaway from CVPR so far: datasets 👏🏼 datasets 👏🏼 datasets 👏🏼
June 12, 2025 at 10:01 PM
Biggest takeaway from CVPR so far: datasets 👏🏼 datasets 👏🏼 datasets 👏🏼
Going to be at CVPR the next couple of days presenting our paper „A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets“.
arxiv.org/abs/2503.17024
Always happy to meet anyone working on representation learning or tabular DL and medical data
arxiv.org/abs/2503.17024
Always happy to meet anyone working on representation learning or tabular DL and medical data
A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets
Supervised contrastive learning (SupCon) has proven to be a powerful alternative to the standard cross-entropy loss for classification of multi-class balanced datasets. However, it struggles to learn ...
arxiv.org
June 11, 2025 at 12:56 AM
Going to be at CVPR the next couple of days presenting our paper „A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets“.
arxiv.org/abs/2503.17024
Always happy to meet anyone working on representation learning or tabular DL and medical data
arxiv.org/abs/2503.17024
Always happy to meet anyone working on representation learning or tabular DL and medical data
Wolt and Uber Eats should start sponsoring conferences. Send them a screenshot of your NeurIPS abstract submission confirmation and get your first delivery free.
May 11, 2025 at 5:28 PM
Wolt and Uber Eats should start sponsoring conferences. Send them a screenshot of your NeurIPS abstract submission confirmation and get your first delivery free.
Deutsche Bahn top form continues with a 45 minute delay on a 3 hour „sprinter“ route…. At this point I’m more mad that it wasn’t at least an hour, then I would have at least gotten compensation
May 5, 2025 at 9:42 PM
Deutsche Bahn top form continues with a 45 minute delay on a 3 hour „sprinter“ route…. At this point I’m more mad that it wasn’t at least an hour, then I would have at least gotten compensation
Praying for some heavy rain and plummeting temperatures soon or this paper isn’t going to be as polished as it could be 😅
May 1, 2025 at 10:49 PM
Praying for some heavy rain and plummeting temperatures soon or this paper isn’t going to be as polished as it could be 😅
Few things more depressing than staying inside all day and working on a paper for a conference deadline in two weeks when it’s a holiday and absolutely amazing weather outside.
The other side of the coin is the freedom to spontaneously take random days off in winter when it snows a lot to go ski!
The other side of the coin is the freedom to spontaneously take random days off in winter when it snows a lot to go ski!
May 1, 2025 at 10:48 PM
Few things more depressing than staying inside all day and working on a paper for a conference deadline in two weeks when it’s a holiday and absolutely amazing weather outside.
The other side of the coin is the freedom to spontaneously take random days off in winter when it snows a lot to go ski!
The other side of the coin is the freedom to spontaneously take random days off in winter when it snows a lot to go ski!
Do animals other than humans also appreciate beauty? Is a falcon flying above the Grand Canyon happier than one flying above Gary, Indiana?
April 29, 2025 at 9:46 PM
Do animals other than humans also appreciate beauty? Is a falcon flying above the Grand Canyon happier than one flying above Gary, Indiana?
After being inspired by this quote by Francis Bacon I have decided to post more online.
April 29, 2025 at 8:03 PM
After being inspired by this quote by Francis Bacon I have decided to post more online.
The co-option of the brightest and most hard working individuals by private enterprise away from government is the biggest loss to civil society in modern history.
April 28, 2025 at 9:24 PM
The co-option of the brightest and most hard working individuals by private enterprise away from government is the biggest loss to civil society in modern history.