ABSTRACT: I will introduce In-Context Operator Networks (ICON), a framework in which a single neural network learns solution operators for differential equations directly from a few prompted input-output examples at inference time, without any weight updates. ICON acts as a few-shot learner across forward and inverse problems for…

ABSTRACT: Open-world mobility describes dynamic real-world environments in which vehicles, robots, infrastructure, and people interact under partial observability, distribution shift, long-tail events, and changing operational conditions. These settings require AI systems that can jointly perform perception, semantic reasoning,…

ABSTRACT: Graph neural networks (GNNs) have emerged as a powerful framework for learning from graph-structured data, yet their theoretical understanding—particularly regarding the behavior of different architectural choices across various graph-based tasks—remains limited. In parallel, random geometric graphs (RGGs) provide a…

ABSTRACT: Deep learning models, despite their power, lag behind the biological brain in interpretability, energy efficiency, and physical plausibility. This presentation explores the mathematical design principles of biological neural circuits -- building upon the classic concept that neural activity is fundamentally driven by…

ABSTRACT: As the Deputy Director for Innovation and Emerging Technologies at the California Governor’s Office of Business and Economic Development (GO-Biz), Tre Bradley is the primary advisor to California state leaders on technology trends and opportunities, focusing on commercialization, technology transfer, and talent pipeline…

ABSTRACT: We seek the ability to take a few images of a scene of interest, and turn it into an immersive visual experience, where one can explore it from different viewpoints, in effect visualizing a 3D representation of an object, scene or photograph, and providing numerous applications in augmented reality, e-commerce and 3D…

ABSTRACT: The experimental sciences have long relied on labor-intensive, manual workflows that limit scalability and slow the pace of research and discovery. Despite advances in instrumentation and data analysis, the act of performing physical experiments remains time-consuming and resource- intensive, ultimately limiting the…

ABSTRACT: The convergence of artificial intelligence and programmable optics is opening new opportunities for both biological imaging and optical machine learning. By shifting complexity from optical hardware to data-driven algorithms and reconfigurable systems, these approaches promise faster, more adaptive, and more efficient…

ABSTRACT: Humans are highly susceptible to framing manipulations in intertemporal decision making—choices that involve tradeoffs between immediate and delayed rewards. Classic biases such as the magnitude effect, in which larger reward amounts increase patience, have been attributed to self-control, reward system activation, and…

ABSTRACT: Modern deep learning is exceptionally good at seeing patterns, but it often sees too much. As models scale, they increasingly begin to see “ghosts", which are nuisance factors that haunt the data and masquerade as true signals. These ghosts appear as stereotypes in social data, as overwhelming thermal emission in…