In this talk, Hsien-Chih will introduce a few topological tools that help us to design extremely efficient algorithms in the plane.

Yang will introduce LARS (Layer-wise Adaptive Rate Scaling) and LAMB (Layer-wise Adaptive Moments for Batch training) optimizers, which can find more parallelism for deep learning.

Aravind will show how the new architecture features in ARM processors can lead to security issues by introducing new attack vectors.

Fundamental findings from several measurements and user studies exploring and understanding the unique behaviors of adversaries as well as benign software developers.

CS Prof. Wojciech Jarosz summarizes some of his group's recent work on accurate, efficient, and controllable physical simulation of light transport.

Developers check source code into a version control system, the code is compiled into software at a build farm, & CI/CD systems run multiple tests to ensure the software’s quality.

Winter term begins

Fall term ends

Music AI systems for intimate human-computer interaction and co-creation.

There is a deep analogy between Bayesian inference and statistical physics.