Logo
2026

Predictive Real2Sim Digital Twins: A World Model Approach to Deformable Mesh and Soft-Body Simulation Physics

2026

Applying world model architectures to predictive physics simulation for deformable objects.

Luke Hollis, Tianxing Fan, Heng Yang
School of Engineering and Applied Sciences, Harvard University
World Models Physics Simulation Digital Twins

Conformal Inference in Language Model Based Survey Simulation

2026

Simulating human behavior with a conformal inference pipeline and LLMs

Naoki Egami, Kosuke Imai, Bingjun Tang, Zhiyu Li
Massachusetts Institute of Technology, Harvard University
Simulation LLMs Digital Twins

Spatiotemporal Representations of Urban Mobility and 3DGS with Remote Sensing

2026

Novel approach to represent urban mobility data with spatiotemporal transformers and language-grounded 3D gaussian splatting.

Luke Hollis, Yasushi Sakai
MIT Media Lab & Harvard University
In Progress
3D Gaussian Splatting Computer Vision Urban Computing