🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We have an upcoming paper at ICLR 2023 on a new feature attribution method for explaining representations learned by unsupervised models! arxiv.org/abs/2210.00107 This was joint work with the fantastic Hugh Chen Chanwoo Kim and my advisor Su-In Lee. (1/n)

My amazing PhD student Ian Covert will present our work on ViT Shapley at #ICLR2023 soon -- Mon 1 May 11 CAT!

MONET by Chanwoo Kim Roxana Daneshjou MD/PhD Su-In Lee et al paper: medrxiv.org/content/10.110… code + model: github.com/suinleelab/MON…

Using #AI to interpret and explain biological age at the individual level thelancet.com/journals/lanhl… The Lancet Healthy Longevity Wei Qiu Matt Kaeberlein Hugh Chen Su-In Lee Allen School

📢 Exciting news! The University of Washington Nathan Shock Center Basic Biology of Aging is hosting the “AI meets Biology of Aging” (AIMBA) virtual workshop on 5/22. Dive into cutting-edge research at the crossroads of AI and geroscience, with our stellar lineup of speakers! sites.google.com/cs.washington.…

Huge congratulations, Su-In Lee! I am so honored to work with you!

From counterfactuals to a new foundation model to promote medical #AI transparency Credit Su-In Lee, Roxana Daneshjou MD/PhD and colleagues Allen School for this exceptional work nature.com/articles/s4159… Nature Medicine nature.com/articles/s4155… Nature Biomedical Engineering

Excited to see our Nature Medicine paper out today led by Chanwoo Kim with my co-senior author Su-In Lee and an amazing team! We used a dermatology foundation model to enable explainable and transparent AI - from auditing datasets to models. nature.com/articles/s4159…

Amazing blog post from first author Chanwoo Kim describing our latest Nature Medicine paper on using a dermatology foundation model to enable explainable AI and dataset/model transparency! Su-In Lee communities.springernature.com/posts/toward-t…

Concept is all you need! Allen School features our Nature Medicine paper on extracting concepts from dermatology images via foundation models, with brilliant first author Chanwoo Kim and exceptional co-senior author Roxana Daneshjou MD/PhD at StanfordDBDS. Details: news.cs.washington.edu/2024/09/11/mon…

While the artist Claude Monet’s paintings can appear blurry and indistinguishable, a new foundational model of the same name from University of Washington UW Engineering #UWAllen’s Su-In Lee and Chanwoo Kim may help bring clarity to medical #AI systems. #UWdiscovers news.cs.washington.edu/2024/09/11/mon…

If you use SHAP, LIME or Data Shapley, check out our new #neurips2024 paper. We introduce stochastic amortization to speed up feature + data attribution by 10x-100x🚀 #XML Surprisingly we can "learn to attribute" cheaply from noisy explanations! arxiv.org/abs/2401.15866 code

I'm hiring: 1. PhD-level Research associate to generate perturbation data 2. ML postdoc to build multimodal generative AI for DNA (eg diffusion and LLM) 3. Bioinformatician (any level) to harmonize functional genomics data for training foundation models DM me if interested!

📢I am on the academic job market this year! My research interest involves utilizing AI and explainable AI to explore the mechanisms of aging and age-related diseases. I'm looking for faculty positions in AI for Biomedicine. Check out my website: qiuweipku.github.io

Happy to share that our work, 'An Efficient Framework for Crediting Data Contributors' has been accepted to ICLR 2026 ICLR2025! 🎉 arxiv.org/abs/2407.03153