๐ก Introducing ๐ฆ๐ฒ๐ป๐๐ผ๐ฟ-๐๐ฎ๐ป๐ด๐๐ฎ๐ด๐ฒ-๐๐ฐ๐๐ถ๐ผ๐ป (๐ฆ๐๐) models โ a new class of models that connect sensor time series, natural language, and actions in one unified framework. ๐ ๐: yang-ai-lab.github.io/OpenSLA ๐: arxiv.org/abs/2607.06617 ๐ป: github.com/yang-ai-lab/... ๐งต
Yuzhe Yang
@yuzheyang.bsky.social
AI Prof @ UCLA | RS @ Google | PhD @ MIT #ML, #AI, #health https://www.cs.ucla.edu/~yuzhe https://yang-ai-lab.github.io/
โ ๐ ๐ผ๐๐ถ๐ผ๐ป ๐ถ๐ ๐๐ป๐ถ๐๐ฒ๐ฟ๐๐ฎ๐น. ๐ง๐ต๐ฒ ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ฏ๐๐ถ๐น๐ ๐ณ๐ผ๐ฟ ๐ถ๐ ๐ฎ๐ฟ๐ฒ ๐ป๐ผ๐. Introducing ๐๐ป๐ฒ๐ฟ๐๐ถ๐ฎ-๐ญ โ a fully open cookbook for building unified wearable motion foundation models. ๐ ๐: yang-ai-lab.github.io/Inertia-1 ๐: arxiv.org/abs/2607.06617 ๐ป: github.com/yang-ai-lab/... ๐งต
Generative models have transformed language and vision. But the physical world runs on something else: ๐จ๐๐ฃ๐จ๐ค๐ง ๐ฉ๐๐ข๐ ๐จ๐๐ง๐๐๐จ. Today, we are excited to introduce ๐ฆ๐ฒ๐ป๐๐ผ๐ฟ๐๐ฒ๐ป โ fully open, large-scale study of generative modeling for real-world sensor time series. ๐: yang-ai-lab.github.io/sensor-gen
I will be at #ICML in Seoul next week! Our group will present 3 papers there: ๐ ๐๐๐๐ฅ๐ง๐ฆ โ Jul 7, 2 PM, Hall A #712 ๐ ๐ฆ๐น๐ฒ๐ฒ๐ฝ๐๐ โ Jul 8, 5 PM, Hall A #4601 ๐ ๐ข๐ฝ๐ฒ๐ป ๐ฆ๐น๐ฒ๐ฒ๐ฝ ๐๐ (๐ข๐ฆ๐) โ Jul 9, 10:30 AM, Hall A #304 I'd be happy to meet and chat! DMs are open. Come say hello! ๐
โค๏ธ ๐๐๐๐ฅ๐ง๐ฆ keeps growing with a new open-source release! yang-ai-lab.github.io/HEARTS Our goal with ๐๐๐๐ฅ๐ง๐ฆ has always been to build a living benchmark for health time-series reasoning. This second wave makes it easier to use, cheaper to evaluate, and more open for the community.
๐ง What if your regression model is learning shortcuts too? Introducing Deep Spurious Regression (DSR) โ our new framework for studying spurious correlations in continuous prediction. ๐งต๐
๐ Excited to share our new Nature paper on passive heart-rate monitoring during everyday smartphone use! ๐ฑ We show that smartphones can estimate heart rate and daily resting heart rate accurately across diverse real-world settings. #AI #DigitalHealth #MobileHealth #HealthAI #Smartphones
Nature research paper: Passive heart-rate monitoring during smartphone use in everyday life go.nature.com/43MqtY0
๐ The website for the ๐๐ฒ๐ฎ๐น๐๐ต ๐๐ป๐๐ฒ๐น๐น๐ถ๐ด๐ฒ๐ป๐ฐ๐ฒ ๐๐ฎ๐ฏ (๐๐๐๐) at UCLA is (finally) live! Check it out โ yang-ai-lab.github.io ๐ข We are hiring! ๐๐๐๐ has multiple openings for postdocs and is also actively recruiting at all levels. Please visit our website for application and contact details! #AI #Hiring
Health Intelligence Lab - UCLA
Advancing scalable, multisensory, and generative AI for healthcare, medicine, and scientific discovery.
yang-ai-lab.github.io
Exciting news for the Health Intelligence Lab at UCLA: 3/3 papers accepted to #ICML (1 as Spotlight) ๐ ๐ฆ๐น๐ฒ๐ฒ๐ฝ๐๐ : ๐ก๐ฎ๐๐๐ฟ๐ฎ๐น-๐๐ฎ๐ป๐ด๐๐ฎ๐ด๐ฒ ๐๐ป๐๐ฒ๐น๐น๐ถ๐ด๐ฒ๐ป๐ฐ๐ฒ ๐ณ๐ผ๐ฟ ๐๐๐บ๐ฎ๐ป ๐ฆ๐น๐ฒ๐ฒ๐ฝ (spotlight) ๐ข๐ฆ๐: ๐ข๐ป ๐ฃ๐ฟ๐ฒ-๐๐ฟ๐ฎ๐ถ๐ป๐ถ๐ป๐ด ๐ฎ๐ป๐ฑ ๐ฆ๐ฐ๐ฎ๐น๐ถ๐ป๐ด ๐ผ๐ณ ๐ฆ๐น๐ฒ๐ฒ๐ฝ ๐๐ผ๐๐ป๐ฑ๐ฎ๐๐ถ๐ผ๐ป ๐ ๐ผ๐ฑ๐ฒ๐น๐ ๐๐๐๐ฅ๐ง๐ฆ: ๐๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ๐ถ๐ป๐ด ๐๐๐ ๐ฅ๐ฒ๐ฎ๐๐ผ๐ป๐ถ๐ป๐ด ๐ผ๐ป ๐๐ฒ๐ฎ๐น๐๐ต ๐ง๐ถ๐บ๐ฒ ๐ฆ๐ฒ๐ฟ๐ถ๐ฒ๐ ๐
Meet OSF โ a fully open benchmark and state-of-the-art sleep foundation models. ๐ We study pre-training and scaling recipes that actually improve generalization in real-world settings. ๐ฅ ๐ Website: yang-ai-lab.github.io/osf/ ๐ป Code: github.com/yang-ai-lab/... ๐ค Models: hf.co/yang-ai-lab/...
Can LLMs really reason over health time series? ๐ Introducing HEARTS โค๏ธโ the first living benchmark built for health time-series reasoning. ๐Website: yang-ai-lab.github.io/HEARTS ๐ต๏ธCode: github.com/yang-ai-lab/... ๐คDataset: hf.co/datasets/yan... ๐Leaderboard: yang-ai-lab.github.io/HEARTS/leade...
๐ What if your sleep signals could speak? Introducing SleepLM โ sleep-language foundation models that turns raw sleep into something we can describe, query, and localize with language. ๐ฃ๏ธ ๐Website: yang-ai-lab.github.io/SleepLM ๐ต๏ธCode: github.com/yang-ai-lab/... ๐คModels: hf.co/yang-ai-lab/... ๐งต๐
๐ข My lab at UCLA is hiring PhD students and postdocs! Please apply to UCLA CS or CompMed and mention my name if you are interested in foundation models and (Gen)AI for health / medicine / science. More info: cs.ucla.edu/~yuzhe
๐จ Let your wearable data "speak" for themselves! โ๏ธ๐ฃ๏ธ Introducing *SensorLM*, a family of sensor-language foundation models, trained on ~60 million hours of data from >103K people, enabling robust wearable sensor data understanding with natural language. ๐งต
๐ฉปโ๏ธ AI underdiagnoses Black female patients A new study found that expert-level vision-language models for chest X-rays systematically underdiagnose marginalised groups โ especially Black women โ more than radiologists. ๐ doi.org/10.1126/sciadv.adq0305 #SciComm #AI #HealthEquity ๐งช
Demographic bias of expert-level vision-language foundation models in medical imaging
Compared to certified radiologists, expert-level AI models show notable and consistent demographic biases across pathologies.
doi.org
Do foundation models in medical imaging see everyone fairly?๐ค Excited to share our new Science Advances paper uncovering & auditing demographic biases of expert-level VLMs, and comparing to board-certified radiologists๐งโโ๏ธ ๐science.org/doi/10.1126/sciadv.adq0305 ๐ปgithub.com/YyzHarry/vlm-fairness (1/)
How multimodal A.I. of real time smartwatch data can automatically detect a person's loss of pulseโsudden cardiac deathโand notify emergency services www.nature.com/articles/s41... @jakesunshine.bsky.social @nature.com
Automated loss of pulse detection on a consumer smartwatch - Nature
Nature - Automated loss of pulse detection on a consumer smartwatch
nature.com
Just published in Nature Biomedical Engineering! Working with the incredible PhD student Wei Qiu and our brilliant collaborator Kamila Naxerova at Harvard was a great pleasure. Our deep profiling framework enables us to view 18 human cancers through the lens of AI! www.nature.com/articles/s41...
Deep profiling of gene expression across 18 human cancers - Nature Biomedical Engineering
Using unsupervised deep learning to generate low-dimensional latent spaces for gene-expression data can unveil biological insight across cancers.
nature.com
A neurologist with 2 APOE4 copies tells us about his experience with #Alzheimers disease washingtonpost.com/wellness/202...
Seven years ago, Scott Lundberg, presented our SHAP framework at the NeurIPS 2017 conference. Since then, SHAP has become one of the most widely used feature attribution methods, with our paper receiving approximately 30,000 citations. It's wonderful that SHAP's birthday aligns perfectly with mine!๐
I will be at #NeurIPS and #ML4H all next week โ let me know if you would like to catch up in person! ๐ข I am also recruiting PhD students! Drop me an email if you're attending NeurIPS and would like to chat or learn more ๐
Hello world! Iโm recruiting ~3 PhD students for Fall 2025 at UCLA ๐ Please apply to UCLA CS or CompMed if you are interested in ML and (Gen)AI for healthcare / medicine / science. See my website for more on my research & how to apply: people.csail.mit.edu/yuzhe
Here is a #compbio starter kit! go.bsky.app/QVPoZXp To all the #Bioinformatics #Genomics #MachineLearning folks: please RP and letโs build this together!
โ๏ธ Check out our latest work on scaling foundation models for large-scale multimodal wearable sensor data!
Scaling wearable foundation models
research.google
Hello world! Iโm recruiting ~3 PhD students for Fall 2025 at UCLA ๐ Please apply to UCLA CS or CompMed if you are interested in ML and (Gen)AI for healthcare / medicine / science. See my website for more on my research & how to apply: people.csail.mit.edu/yuzhe