
Marinka Zitnik
@marinkazitnik
Associate Professor at Harvard | Faculty @Harvard @KempnerInst AI | Faculty @broadinstitute @harvard_data | Cofounder @ProjectTDC | @AI_for_Science
ID: 61502457
https://zitniklab.hms.harvard.edu 30-07-2009 14:34:38
2,2K Tweet
7,7K Followers
224 Following

Congrats LOGML Summer School for running an in-person grad ML summer school at Imperial College London and opening up research opportunities for students worldwide! ๐ logml.ai Thanks to organizers, Valentina Giunchiglia, and mentors Guadalupe Gonzalez Chirag Agarwal Ruthie Johnson Yasha Ektefaie


๐ Excited to open up our global evaluation of AI for drug decision-making and therapeutic reasoning Shanghua Gao Want to shape the future of therapeutic AI, from understanding existing medicines to developing new treatments for diseases with limited options? Start here:



Announcing AI for Science at NeurIPS Conference 2025! Join us in discussing the reach and limits of AI for scientific discovery ๐ ๐ Workshop submission deadline: Aug 22 ๐ก Dataset proposal competition: more details coming soon! โจ Amazing line up of speakers and panelists


Join us at the AI for Science NeurIPS Conference workshop to discuss the reach and limits of AI for scientific discovery AI for Science Excited to continue the series of #AIforScience workshops: ai4sciencecommunity.github.io Ada Fang Yuanqi Du Lixue Cheng Sanjeev Raja Michael Albergo

Join us at ICML ICML Conference this Thu 17 Jul from 4:30-7 pm PT to learn about MedTok and try it out! Congrats to Xiaorui Su Shvat MedTok is a general-purpose tokenizer of medical codes that can be integrated into any transformer or tokenization based biomedical AI By

๐จ I'm excited to share that MedTok, our multimodal medical code tokenizer, has been accepted to #ICML2025! ๐ Try out MedTok and see how it can enhance biomedical AI applications. huggingface.co/mims-harvard/Mโฆ Huge thanks to Marinka Zitnik and all my amazing collaborators!


๐ฃ Competition launch alert! CUREBench competition at NeurIPS Conference 2025 Start here: curebench.ai Benchmarking AI for therapeutic reasoning, drug discovery, treatment planning, and therapeutic decision-making ๐ฏ Track 1: Develop AI models that rely on parametric


Enjoyed speaking with The New Yorker on what makes todayโs AI better at therapeutic reasoning than past models To test reasoning models deeply and broadly, join our CUREBench competition at NeurIPS Conference 2025 Start here: curebench.ai


Excited to see that 130+ teams have already entered CUREBench NeurIPS Conference 2025 Challenge Start here: curebench.ai Evaluate AI deeply and broadly for therapeutics Shanghua Gao CZI Science Milken Institute Biswas Family Foundation CZI Science Rare as One program Harvard Medical School


Thank you for organizing the session Pengtao Xie

Great to see students from DBMI at Harvard Medโs AIM 2 course presenting their class research at ICML Conference ICMLโ25 in Vancouver last week ๐๐ Valentin, Shyam, and John developed this project for BMI 702 (AI in Medicine II, zitniklab.hms.harvard.edu/AIM2) and were mentored by the stellar TF


๐ 260+ teams have entered the CUREBench NeurIPS Conference 2025 Challenge! ๐ curebench.ai Challenge Tracks: โข Track 1: AI models relying solely on built-in memory โข Track 2: AI systems that leverage external tools and resources Evaluation is by agentic judges


Data is everything. We need more data to unlock the next scientific breakthroughs with AI. Hereโs how weโre addressing this at NeurIPS. With a $10,000 prize pool to get it started. ๐งต NeurIPS Conference AI for Science Renaissance Philanthropy #NeurIPS2025



What if AI virtual cells could help us decode disease, test medication, and rewrite biology? Read the latest edition of Future Explored here: freethink.com/artificial-intโฆ @kristinjhouser @tkaraletsos CZI Science Marinka Zitnik Arc Institute Dave Burke #FutureExplored #AI
