Jiayi (Eris) Zhang

Stanford University

Position: Ph.D. Candidate
Rising Stars year of participation: 2024
Bio

Jiayi (Eris) Zhang is a 4th-year PhD candidate at Stanford University, advised by Prof. Doug James. She earned her undergraduate degree in Computer Science and Mathematics from the University of Toronto, where she conducted research under the supervision of Prof. Alec Jacobson. Her research focuses on physics-based animation, geometry processing, and numerical optimization. Currently, her work is primarily centered on developing intelligent algorithms, models, and tools to enhance creativity and productivity in design, animation, and simulation, with a particular focus on level-of-detail simulation techniques. She has also interned at Adobe over several summers, collaborating closely with Dr. Danny Kaufman.

Areas of Research
  • Computer Graphics and Vision
ADAPTS: Adaptive Level-of-Detail Simulation and Progressive Techniques for Scalable Experiences

In today’s tech renaissance, high-performance computing, personal imaging devices and AR/VR innovations are redefining the digital landscape. To achieve truly immersive experiences, advanced physics-based modeling and simulation are critical for transforming static digital environments into dynamic, interactive spaces where large-scale audiences can engage, learn, discover, and express themselves. However, a dilemma all modeling and simulation tasks face is the fundamental trade-off between speed and fidelity/accuracy, especially in large-scale systems. Coarse, low-poly scenes allow for rapid design iterations and real-time interaction but often compromise expressiveness and accuracy, leading to artifacts and detracting from immersive experience. Conversely, high-resolution meshes and complex physical interactions offer superior fidelity through high-fidelity simulations, but demand slow, detailed modeling and simulations, making them impractical for real-time applications. By adapting the ‘level-of-detail’ concept from rendering (e.g., Nanite 5) and geometry to physical simulation, my research seeks to dynamically balance speed and fidelity. For example, this approach provides coarse previews when computational resources are limited or the viewpoint is distant, with progressively refined details as resources increase and the viewpoint draws closer. By extending this concept to broader simulation scenarios, active character control, and efficient computation across large distributed systems, my research aims to create a practical coarse-to-fine simulation framework and interactive system that supports scalable physics-based storytelling, animation authoring, and immersive 2D and 3D experiences. My ultimate research goal is to balance speed, fidelity, and controllability, effectively lowering the barrier to using simulation in real-world production pipelines.