Kaifeng Zhang
@kaiwynd • 2,806 subscribers
PhD student at Columbia University
Shorts
Videos
🧵 Evaluating robot policies in the real world is slow, expensive, and hard to scale. During my internship at SceniX AI this summer, we had many discussions around the two key questions: how accurate must a simulator be for evaluation to be meaningful, and how do we get there? Our new framework, Real2Sim-Eval, takes a step toward that answer. By combining Gaussian Splatting for photorealistic rendering and soft-body digital twins for realistic dynamics, we make simulation predictive of real-world performance. 👉
Kaifeng Zhang61,813 views • 8 months ago
No more content to load