@PatrickYu69606 Profile picture

Patrick Yu

@PatrickYu69606

Machine Learning and Computational Biology PhD student @uwcse, previously undergrad @IllinoisCS

Joined July 2023
Patrick Yu Reposted

Excited to share OCTCube (arxiv.org/abs/2408.11227), the first *3D* foundation model for retinal OCT images. OCTCube is trained on 26k 3D OCT volumes encompassing 1.62 million 2D images. OCTCube achieved significantly best performance on 27 out of 29 tasks.

Tweet Image 1

Patrick Yu Reposted

I have many ideas including extending my work to incorporate task complexity...but not enough time in the day sadly. But Rylan has the most recent work I've done and we are extending it in the fine-tuning regime! Check my alignment coefficient work too dmlr.ai/accepted/ !


Patrick Yu Reposted

It was a pleasure working with co-first author Alex DeGrave along with advisors @suinleelab and @RoxanaDaneshjou! Check out our paper at: medrxiv.org/content/10.110…


Patrick Yu Reposted

Our "official" Tweeprint following-up "the Mirage paper". I genuinely learned a lot about the (un)predictability of LLM capabilities (evals) on this project. I hope you enjoy the learning as much as I did. 🧠 Reference to the original "Mirage" Tweeprint: x.com/sanmikoyejo/st…

❤️‍🔥❤️‍🔥Excited to share our new paper ❤️‍🔥❤️‍🔥 **Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?** w/ @haileysch__ @BrandoHablando @gabemukobi @varunrmadan @herbiebradley @ai_phd @BlancheMinerva @sanmikoyejo arxiv.org/abs/2406.04391 1/N

Tweet Image 1


Patrick Yu Reposted

Excited to see our research supporting the launch of the free AI-based biological age test in the @novoslabs Life app. Check out the new features for personalized insights and guidance! Read our paper for more details: thelancet.com/journals/lanhl…

NOVOS launches free AI-based biological age test New test available in @novoslabs Life app boasts personalized features, including Lifestyle score, recommendations and AI chat guidance. @SlowMyAge #diagnostics #AI #biologicalage #app #longevity longevity.technology/news/novos-lau…



Patrick Yu Reposted

🔥🔥Super excited to share our GigaPath paper @Nature! Model: huggingface.co/prov-gigapath/… Code: github.com/prov-gigapath/… Really enjoy the journey towards ultimate patient care and clinical discovery! This is just the beginning!

Just out @Nature The 1st whole-slide digital pathology #AI foundation model pre-trained on large-scale real-world data, from over 1.3 billion images, 30,000 patients nature.com/articles/s4158… @hoifungpoon @HanwenXu6 @Microsoft @UW @naotous @MSFTResearch

Tweet Image 1
Tweet Image 2


Patrick Yu Reposted

Just out @Nature The 1st whole-slide digital pathology #AI foundation model pre-trained on large-scale real-world data, from over 1.3 billion images, 30,000 patients nature.com/articles/s4158… @hoifungpoon @HanwenXu6 @Microsoft @UW @naotous @MSFTResearch

Tweet Image 1
Tweet Image 2

Patrick Yu Reposted

Excited to announce the inaugural AIMBA (AI Meets Biology of Aging) 2024 meeting on May 22, 2023, 9-2pm PT, organized by @UW @NathanShockCtrs ! Featuring four keynote speakers: Profs @mariabrbic, Anne Brunet, Vadim Gladyshev, @james_y_zou Check it out! sites.google.com/cs.washington.…

Tweet Image 1

📅The deadline to submit abstracts for the AIMBA (AI Meets Biology of Aging) workshop has been extended to April 30th! We look forward to seeing your awesome contributions to AI & aging biology! sites.google.com/cs.washington.…


Patrick Yu Reposted

Happy to share that our paper on leveraging foundation models to foster the explainability and transparency of medical AI has been published today in @NatureMedicine! Check it out here: nature.com/articles/s4159…


Patrick Yu Reposted

One of the reasons I love Cal Newport's journal for time blocking. What is your favorite way to feel organized so you can focus more deeply?

Tweet Image 1

Patrick Yu Reposted

Way to go @weiqiu55 !

My first paper in aging research! The beginning of a journey dedicated to unlocking the mysteries of aging. Eager to delve deeper and contribute more fantastic research to this fascinating field with @suinleelab news-medical.net/news/20231109/…



Patrick Yu Reposted

Excited to announce our "deep profiling" of 18 human cancers! Incorporating all available cancer expression data into DNNs was my first idea 14 years ago when joining UW. Honored to work with brilliant minds, @weiqiu55 @uwcse and @naxerova @harvardmed! biorxiv.org/content/10.110…


📢Announcing the 1st AIMBA (AI Meets Biology of Aging) virtual workshop on 5/22 featuring speakers at the forefront of AI & aging research, at @halo_uw w/ fantastic co-organizers @weiqiu55 @suinleelab! 📅Submit abstracts by April 22! Register here: sites.google.com/cs.washington.…


Patrick Yu Reposted

📢 Exciting news! The @uw 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.…


Patrick Yu Reposted

Excited to share our #ICML #ICML2023 workshop paper: **Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data** Co-lead with @_alycialee joint w/ @sanmikoyejo arxiv.org/abs/2306.13840 #NLP #ML #LLM 1/13

Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data paper page: huggingface.co/papers/2306.13… Current trends to pre-train capable Large Language Models (LLMs) mostly focus on scaling of model and dataset size.…

Tweet Image 1


United States Trends
Loading...

Something went wrong.


Something went wrong.