Bio
I am a fifth-year Ph.D. student in the Computational Design & Fabrication Group at MIT CSAIL, supervised by Prof. Wojciech Matusik. I received my M.Phil. from The Chinese University of Hong Kong and my Bachelor's degree from Tsinghua University.
I build design‑ready world simulators. Generative foundation models are scaling fast, yet the real world is the ultimate judge: a model is only useful if its predictions stay physically consistent under real dynamics and constraints. Achieving this at scale runs into a data wall: high‑quality interaction data and high‑fidelity physical signals are costly and scarce. My goal is to push past this wall with scalable multimodal pretraining while enforcing physical realizability.
I use two north‑star metrics: (i) Emergent capability from native multimodal data: capability improves with data/model/compute, driven by geometry and dynamics (beyond language‑only supervision). (ii) Real‑world realizability for computational design: outputs satisfy physical constraints and translate into designs that are manufacturable, synthesizable, and reliable in the real world.
Scalability and realizability can seem at odds: scale prefers generic throughput; realizability comes with feasibility bounds. I view them as a constrained optimization: maximize capability with scale, subject to physical constraints that define what a valid world/design is. My recent work includes scalable pretraining for world simulation (this), differentiable projection modules (this, this), and physics‑aware representations (this, this, this). Together, they enable faster iteration and physically faithful, data‑efficient generation from molecular materials and proteins to engineered 3D shapes.
Selected Initiatives
Graphics4Science 2026: Graphics for Cross-Scale Reliable Scientific Instruments
Minghao Guo,
Mina Konaković Lukovic,
Qixing Huang,
Yin Yang,
Chenfanfu Jiang,
Wojciech Matusik,
Peter Yichen Chen
SIGGRAPH Workshop 2026
Graphics4Science: Computer Graphics for Scientific Impacts
Peter Yichen Chen*,
Minghao Guo*,
Hanspeter Pfister,
Ming Lin,
William Freeman,
Qixing Huang,
Han-wei Shen,
Wojciech Matusik
SIGGRAPH Course 2025
Selected Publications
For full publication list, please refer to my Google Scholar page.
GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training
Haixu Wu*,
Minghao Guo*,
Zongyi Li,
Zhiyang Dou,
Mingsheng Long,
Kaiming He,
Wojciech Matusik
arXiv
*=equal contribution
Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection
Siyuan Chen*,
Minghao Guo*†,
Caoliwen Wang,
Anka He Chen,
Yikun Zhang,
Jingjing Chai,
Yin Yang,
Wojciech Matusik,
Peter Yichen Chen†
ICLR 2026
*=equal contribution, †=corresponding author
Electronic-Free Particle Robots Communicate through Architected Tentacles
Xinyi Yang,
Bohan Wang,
Víctor Riera Naranjo,
Minghao Guo,
Olivia Rivera,
Leonid Sopizhenko,
Shucong Li,
William Freeman,
Wojciech Matusik,
Bolei Deng
Advanced Intelligent Systems
Selected as Cover Picture
FlashBias: Fast Computation of Attention with Bias
Haixu Wu,
Minghao Guo,
Yuezhou Ma,
Yuanxu Sun,
Jianmin Wang,
Wojciech Matusik,
Mingsheng Long
NeurIPS 2025
TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes
Minghao Guo*,
Bohan Wang*,
Kaiming He,
Wojciech Matusik
ICLR 2025
Oral Presentation [acceptance rate: 1.8%]
*=equal contribution
Physically Compatible 3D Object Modeling from a Single Image
Minghao Guo,
Bohan Wang,
Pingchuan Ma,
Tianyuan Zhang,
Crystal Elaine Owens,
Chuang Gan,
Joshua B. Tenenbaum,
Kaiming He,
Wojciech Matusik
NeurIPS 2024
Spotlight
Medial Skeletal Diagram: A Generalized Medial Axis Approach for 3D Shape Representation
Minghao Guo*,
Bohan Wang*,
Wojciech Matusik
SIGGRAPH Asia 2024 (Journal Track)
*=equal contribution
Representing Molecules as Random Walks Over Interpretable Grammars
Michael Sun,
Minghao Guo,
Weize Yuan,
Veronika Thost,
Crystal Elaine Owens,
Aristotle Franklin Grosz,
Sharvaa Selvan,
Katelyn Zhou,
Hassan Mohiuddin,
Benjamin J. Pedretti,
Zachary P. Smith,
Jie Chen,
Wojciech Matusik
ICML 2024
Spotlight
Variational Quasi-harmonic Maps for Computing Diffeomorphisms
Yu Wang,
Minghao Guo,
Justin Solomon
SIGGRAPH 2023 (Journal Track)
Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
Minghao Guo,
Veronika Thost,
Samuel Song,
Adithya Balachandran,
Payel Das,
Jie Chen,
Wojciech Matusik
ICML 2023
Data-Efficient Graph Grammar Learning for Molecular Generation
Minghao Guo,
Veronika Thost,
Beichen Li,
Payel Das,
Jie Chen,
Wojciech Matusik
ICLR 2022
Oral Presentation [acceptance rate: 1.6%]
PolyGrammar: Grammar for Digital Polymer Representation and Generation
Minghao Guo,
Liane Makatura,
Wan Shou,
Timothy Erps,
Michael Foshey,
Wojciech Matusik
Advanced Science
Pareto Gamuts: Exploring Optimal Designs Across Varying Contexts
Liane Makatura,
Minghao Guo,
Adriana Schulz,
Justin Solomon,
Wojciech Matusik
ACM Transactions on Graphics 2021 (SIGGRAPH 2021)