Jan Clusmann
@janclusmann.bsky.social
Clinician Scientist, Clinical AI Researcher, LLM Enthusiast, Climate Advocate
Reposted by Jan Clusmann
Wrapped up #CCESummSchool25 with inspiring talks on early cancer + recognition session! Congratulations to Sena Alptekin @dkfz.bsky.social, Marck Opdam @nkinl.bsky.social, @janclusmann.bsky.social for Best Posters and Francesca Cogo @vhio.bsky.social for Best Participant Talk! 🎉
October 10, 2025 at 12:36 PM
Wrapped up #CCESummSchool25 with inspiring talks on early cancer + recognition session! Congratulations to Sena Alptekin @dkfz.bsky.social, Marck Opdam @nkinl.bsky.social, @janclusmann.bsky.social for Best Posters and Francesca Cogo @vhio.bsky.social for Best Participant Talk! 🎉
Thank you for sharing! It was a pleasure working on this, together with @twittlabs.bsky.social , @jnkt.bsky.social and many others...
Case Study by J. Clusmann et al.: Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology nejm.ai/4mrSoEW
@janclusmann.bsky.social #AI #MedSky #DigitalHealth
@janclusmann.bsky.social #AI #MedSky #DigitalHealth
June 30, 2025 at 1:49 PM
Thank you for sharing! It was a pleasure working on this, together with @twittlabs.bsky.social , @jnkt.bsky.social and many others...
Great visit to EKFZ Digital Health Institute! Gave a talk at Jakob Kather’s lab, had great 1:1s with team members, and visited our PhD student Elisa Merelli, who's spending part of her PhD here💡🔬 #DigitalHealth #AI #Research
@jnkt.bsky.social @janclusmann.bsky.social
@jnkt.bsky.social @janclusmann.bsky.social
June 10, 2025 at 3:34 PM
Reposted by Jan Clusmann
Great visit to EKFZ Digital Health Institute! Gave a talk at Jakob Kather’s lab, had great 1:1s with team members, and visited our PhD student Elisa Merelli, who's spending part of her PhD here💡🔬 #DigitalHealth #AI #Research
@jnkt.bsky.social @janclusmann.bsky.social
@jnkt.bsky.social @janclusmann.bsky.social
June 10, 2025 at 3:32 PM
Great visit to EKFZ Digital Health Institute! Gave a talk at Jakob Kather’s lab, had great 1:1s with team members, and visited our PhD student Elisa Merelli, who's spending part of her PhD here💡🔬 #DigitalHealth #AI #Research
@jnkt.bsky.social @janclusmann.bsky.social
@jnkt.bsky.social @janclusmann.bsky.social
Finally out, in NEJM AI!
Everyday labels and watermarks can override medical knowledge of vision language models, just by their presence.
Was a lot of fun to work on this with @twittlabs.bsky.social , @jnkt.bsky.social and many others
Everyday labels and watermarks can override medical knowledge of vision language models, just by their presence.
Was a lot of fun to work on this with @twittlabs.bsky.social , @jnkt.bsky.social and many others
Excited to share our new publication in @ai.nejm.org „Incidental Prompt Injections on Vision-Language Models in Real-Life Histopathology“. Important work together with our amazing colleagues @janclusmann.bsky.social @jnkt.bsky.social @markuseckstein3.bsky.social et al. ai.nejm.org/stoken/defau...
Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology
Vision–language models (VLMs) can analyze multimodal medical data. However, a significant weakness of VLMs is their susceptibility to prompt injection attacks. Here, the model receives conflicting ...
ai.nejm.org
May 26, 2025 at 5:30 AM
Finally out, in NEJM AI!
Everyday labels and watermarks can override medical knowledge of vision language models, just by their presence.
Was a lot of fun to work on this with @twittlabs.bsky.social , @jnkt.bsky.social and many others
Everyday labels and watermarks can override medical knowledge of vision language models, just by their presence.
Was a lot of fun to work on this with @twittlabs.bsky.social , @jnkt.bsky.social and many others
The autoimmune hepatitis field is quite unique in the way clinicians and researchers on AIH are connected personally worldwide. Optimal starting point for generalizable prediction algorithms ...
February 18, 2025 at 1:30 PM
The autoimmune hepatitis field is quite unique in the way clinicians and researchers on AIH are connected personally worldwide. Optimal starting point for generalizable prediction algorithms ...
www.bmj.com/content/388/...
The disruptions of free research in the US is concerning, for the whole scientific community. Highly recommended opinion article to understand, why the voices of US science have been so quiet lately.
The disruptions of free research in the US is concerning, for the whole scientific community. Highly recommended opinion article to understand, why the voices of US science have been so quiet lately.
Anger, despair, and defiance from a voice within the US federal research system
People around the world are watching with disbelief as the new US government closes down its aid programme, withdraws from the World Health Organization (WHO) and the Paris agreement on climate change...
www.bmj.com
February 16, 2025 at 1:04 AM
www.bmj.com/content/388/...
The disruptions of free research in the US is concerning, for the whole scientific community. Highly recommended opinion article to understand, why the voices of US science have been so quiet lately.
The disruptions of free research in the US is concerning, for the whole scientific community. Highly recommended opinion article to understand, why the voices of US science have been so quiet lately.
So happy to share this: secret instructions hidden in images can terribly alter the output of VLMs to create misdiagnosis. Models have different susceptibility, though, with Claude3.5 apparently being much better aligned to ethical outputs than GPT4o.
#aisafety
#LLMs
#VLMs
#aisafety
#LLMs
#VLMs
Very happy to share our latest paper, led by Jan Clusmann: Prompt injection attacks on vision language models in oncology. We show how VLMs in healthcare can be easily hacked and prompted to create harmful output. www.nature.com/articles/s41...
February 9, 2025 at 1:49 PM