Audience: Alumni
-

Shields, S. (CM) – Procedural, Player-Centric Game Balancing
Game balance is a term widely used among players, researchers, and designers of games. It is a concept that feels vitally important to how we make and play games – […]
-

Fan, Y. (CSE) – Building Human-Centered Multimodal AI Agents
As multimodal artificial intelligence systems become increasingly embedded in everyday technology, there is a growing need to design human-centered AI agents that support and amplify human capabilities rather than replace […]
-

Mashhadi, N. (CSE) – Compositional, Clinically Conditioned, and Confound-Aware Deep Learning for Alzheimer’s Disease Neuroimaging
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and a leading cause of dementia. Neuroimaging and clinical biomarkers can reveal early disease changes, but building reliable machine learning models is […]
-

“The Cigarette Surfboard” screening with filmmaker Ben Judkins (Kresge ’17)
Join Banana Slug alumni filmmaker Ben Judkins (Kresge ’17, film and digital media) and “ciggy board” creator Taylor Lane for a screening of their award-winning documentary, The Cigarette Surfboard (presented by the California Coastal Commission‘s […]
-

Xu, Y. (CSE) – Right Place, Right Time: Accelerating Edge Computation on Modern Heterogeneous SoCs
Modern edge computing increasingly relies on heterogeneous System-on-Chip (SoC) architectures. These chips tightly integrate general-purpose CPUs with various specialized accelerators, including GPUs, FPGAs, and AI accelerators, all under a shared […]
-

What’s new in AI?
Lead innovation as a machine learning engineer Want to learn what’s new in AI? Join Praveen Krishna, chair of the Artificial Intelligence Application Development certificate program, in an informal discussion […]
-

Liu, C. (CSE) – Enabling LLM Unlearning at Inference Time by Decomposing Detection and Intervention
Machine unlearning addresses the “right to be forgotten” under GDPR and enables privacy, copyright, and safety compliance in large language models. Training-based unlearning can remove targeted behavior on benchmarks, but […]
-

Fredrickson, K. (CSE) – Practical Anonymity with Formal Resistance to Traffic Analysis
Anonymous communication systems hide who is talking to whom, not just what is said. However, existing systems are either vulnerable to traffic analysis attacks–attacks where adversaries observe and correlate the […]

