talks

Download

talks@lists.cs.princeton.edu

August 2026

2 participants
2 discussions

27 Aug '26

Joshua Aduol will present his FPO "Integrating Physical Structure into Machine Learning: PDE Constraints and Differentiable Dynamics" on Monday, August 31, 2026 at 10:00 AM in CS 401. The members of Joshua’s committee are as follows: Examiners: Ryan Adams (Adviser), Szymon Rusinkiewicz, Christine Allen-Blanchette Readers: Ryan Adams (Adviser), Peter Orbanz (University College London) A copy of his thesis is available upon request. Please email gradinfo(a)cs.princeton.edu if you would like a copy of the thesis. Everyone is invited to attend the talk. Abstract follows below: Despite strong empirical performance, many machine learning models ignore the governing physical laws underlying the data they model. This thesis presents some techniques to address these shortcomings in two complementary directions: 1) enforcing partial differential equations (PDE) constraints in neural networks, and 2) differentiable rigid body dynamics simulation of closed-loop kinematic chains. Within these directions, we present three contributions. In the first project, we develop a method to construct neural networks that output a time-dependent probability density and the corresponding flow field. The approach leverages recent developments in divergence-free neural networks and enables joint modeling without the need of a numerical integrator to compute one from the other. We evaluate it against continuous normalizing flows demonstrating competitive performance with improved computational efficiency. Extending this idea, we then develop a generalization of divergence-free neural networks to enforce underdetermined linear PDE constraints. Using results from PDE theory on the invertibility of linear differential operators, we construct models that satisfy these constraints by design. This yields a flexible framework for PDE-constrained learning problems. We validate the approach against physics-informed neural network baselines demonstrating improved accuracy. Finally, we present a differentiable rigid-body dynamics simulator that natively supports closed-loop mechanisms and enables large-scale vectorized simulation on GPUs. We describe the design principles underlying the system and demonstrate its use in learning controllers for multiple closed-loop mechanisms in parallel, as well as simulating a variety of mechanisms in parallel and comparing it to state-of-the-art differentiable simulators. Together, these contributions advance the integration of physical structure into machine learning models, improving their consistency, efficiency, and applicability to real-world systems.

2 1

HAPPENING NEXT WEEK: Emerging Frontiers in Computer Architecture and Systems Seminar | Sophia Shao, UC Berkeley, 4:30PM B205 EQuad
by Emily C. Lawrence 26 Aug '26

26 Aug '26

Emerging Frontiers in Computer Architecture and Systems Seminar Speaker: Yakun Sophia Shao, University of California-Berkeley Title: From Closed-Loop Systems to Closed-Loop Design: Full-Stack Co-Design for the AI Era Day: Thursday, September 3, 2026 Time: 4:30 PM Location: B205 Engineering Quadrangle Hosts: Sneha Goenka Abstract: This lecture presents the latest innovations in mmWave antenna-in-package (AiP) technologies as a key enabler of high-performance wireless communication and sensing systems. It covers advancements in high-frequency packaging substrates for compact multi-layer AiP integration, along with signal and power integrity challenges and solutions. The lecture also includes heterogeneous integration approaches, measurement methodologies and results, as well as an introduction to the emerging Antennas-to-AI platform concept. Bio: Professor Yakun Sophia Shao is The Class of 1951 Chair Associate Professor at the Electrical Engineering and Computer Sciences department of University of California, Berkeley. Her research interests are in the area of computer architecture, with a special focus on specialized accelerator, heterogeneous architecture, and agile VLSI design methodology. Previously, she was a Senior Research Scientist at NVIDIA Research and received her Ph.D. degree in 2016 from Harvard University. She is a recipient of the 2025 Outstanding Teaching Award in EE, the 2024 Anita Borg Early Career Award, a Sloan Research Fellowship, an NSF CAREER Award, the 2022 IEEE TCCA Young Computer Architect Award, a Google Faculty Rising Stars Award in Systems Research, a Google Research Scholar Award, a Facebook Research Award, an Okawa Foundation Research Grant, and the inaugural Dr. Sudhakar Yalamanchili Award. Her work has been awarded multiple Best Paper Awards and Distinguished Artifact Awards at major hardware conferences.

1 0