Rose Yu
@yuqirose
Machine Learning Prof @UCSanDiego, Scholar @amazon, Previously @google, @Northeastern, @Caltech, @USC, #Physics-Guided #AI, MIT TR-35 Innovator.
Our 500+ page AI4Science paper is finally published: Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems. Foundations and Trends® in Machine Learning, Vol. 18, No. 4, 385–912, 2025 nowpublishers.com/article/Detail…
Organizing team: @AdaFang_, @YuanqiD, @SherryLixueC, Sanjeev Raja, @msalbergo, @LijingWang8, Carla Gomes, @wellingmax, @marinkazitnik. Sign up for Area Chair: docs.google.com/forms/d/e/1FAI… Sign up to be a reviewer: docs.google.com/forms/d/e/1FAI…
When and why are neural network solutions connected by low-loss paths? In our #ICML2025 paper, we show that mode connectivity often arises from symmetries—transformations of parameters that leave the network’s output unchanged. Paper: arxiv.org/abs/2505.23681 (1/6)
I’m happy to share that I’m starting a new position as Amazon Scholar at @amazon!
Excited to speak at NAS tonight!
Reminder! Join Rose Yu (@yuqirose) of @UCSanDiego tonight at 7 pm PT for her Distinctive Voices talk on Physics-Guided AI, a framework that can accelerate scientific discovery by integrating #physics into data-driven methods. Attend online or in person: ow.ly/BCjY50VWAHg
How can we integrate physical laws into AI? 🧠⚙️ On June 4, join Rose Yu (@yuqirose) of @UCSanDiego for a Distinctive Voices talk on Physics-Guided AI—a framework that fuses #physics with machine learning to boost accuracy, efficiency & insight. Register: ow.ly/A1RK50VWAug