Keynote Presentations

• From Constraints to Co-Creation Architecting a Real-Time Engine for AI
• Bridging Generative Models and Physical Priors for 3D Reconstruction
• Let’s not forget… Creating Great Interactive 3D Worlds Requires Designing Great Interactions
• Naty Hoffman

From Constraints to Co-Creation Architecting a Real-Time Engine for AI

Blake Taylor

Bio

Blake Taylor is the Technical Lead for Meta Horizon Engine (MHE), where he leads the architecture and delivery of Meta’s native engine for Horizon—raising the bar on performance, visual fidelity, and scalability across products and teams. He has spent his career building real-time graphics and simulation systems across platforms, from mixed reality to GPUs and game engines. Prior to Meta, Blake served as Magic Leap’s executive technical lead for graphics, setting mixed reality rendering strategy and end-to-end architecture while leading teams delivering the graphics stack and perception platform. Earlier, he worked at Intel on Direct3D driver performance and game/ISV enablement across Larrabee and Intel integrated GPUs, and at Raytheon on theater-scale real-time visualization and simulation.

Bridging Generative Models and Physical Priors for 3D Reconstruction

Dor Verbin

Bio

Dor Verbin is a research scientist at Google DeepMind in San Francisco, where he works on computer vision, computer graphics, and machine learning. He received his Ph.D. in computer science from Harvard University. Previously, he received a double B.Sc. in physics and in electrical engineering from Tel Aviv University, after which he worked as a researcher at Camerai, developing real-time computer vision algorithms for mobile devices. He received the Best Student Paper Honorable Mention award at CVPR 2022.

Let’s not forget… Creating Great Interactive 3D Worlds Requires Designing Great Interactions

Kayvon Fatahalian

Bio

Kayvon Fatahalian is Associate Professor of Computer Science at Stanford University, where he leads a research group building computing systems for advanced computer graphics and AI applications. His group's recent work spans high-performance simulation of virtual environments for AI training including the Madrona game engine, designed to simulate thousands of environments at millions of frames per second, large-scale video analysis (from a decade of US cable TV news to broadcast tennis video turned into controllable, interactive characters that look and behave like star players), and human-in-the-loop machine learning systems for creative workflows and rapid model development. Before joining Stanford, he was a faculty member at Carnegie Mellon University, where he taught parallel computer architecture and visual computing systems. He earned his Ph.D. at Stanford in 2011 with a dissertation on evolving the real-time graphics pipeline for micropolygon rendering, and his work appears regularly at SIGGRAPH, I3D, and High Performance Graphics.

Naty Hoffman

Bio

Naty Hoffman is currently retired after a 35-year career at companies including Meta (improving the appearance of Meta Avatars), Lucasfilm (designing and implementing advanced rendering algorithms for virtual production and VR), 2K Games (leading technology development), Activision (advancing graphics R&D for many games including the Call of Duty series), Santa Monica Studio (coding graphics technology for God of War III), Naughty Dog (developing low-level Playstation 3 libraries), Westwood Studios (leading graphics development on Earth and Beyond) and Intel (architecting CPU pipeline modifications and working on early x86 SIMD extensions). Naty has also authored influential publications and presentations on topics including physically based shading, cinematic lighting, and color perception in graphics.