CTRL-G: Controllable Generative Graphics for Games

Generative AI is rapidly transforming game development, enabling new approaches to content creation, simulation, and player interaction. However, for interactive systems, the central challenge is not generation alone, but control—the ability to steer generative models in real time, align them with player intent, and integrate them into production pipelines.

Performance, Rendering, and Interaction in Competitive Esports (PRICE)

Esports is having a significant societal impact. Yet scheduling competitive group play during experiments is difficult, and recreating competitive environments in the lab is challenging. To address these problems, we adopt the field experiment methodology, to create hybrid tournament-experiments — experimentation integrated into the tournament itself. We run two Rocket League tournament-experiments and discuss their methodological and experimental implications.

Haithem Turki

Haithem's research focuses on reconstructing, simulating, and generating dynamic 3D worlds, with a particular interest in the intersection of reconstruction and generative modeling. His recent work spans scalable neural scene reconstruction, real-time sensor simulation, and 3D content generation. He obtained his Ph.D.

Jian Hu

Sheng-Yu Huan

Igor Markov

Ryan Punamiya

Jaydeep Kulkarni

Ziyi Zhang

Ziyi is a Research Scientist in NVIDIA’s Real-Time Graphics Research group, with research focused on light transport simulation and differentiable rendering. Before joining NVIDIA, Ziyi completed a Ph.D. in the Realistic Graphics Lab at EPFL, advised by Professor Wenzel Jakob. A complete list of publications can be found on Ziyi’s personal website.

Sixu Li

Sixu joined the Accelerators & VLSI Research (AVR) group in 2026, after interning with the group during the summers of 2024 and 2025. His research interests include digital circuits & systems, and neural rendering.

Before beginning his Ph.D., he worked in the High-Performance Computing Department at Sensetime Research from 2021 to 2022, where he focused on designing low-power, end-to-end simultaneous localization and mapping (SLAM) accelerators for edge AR/VR platforms.

Subscribe to