Chiyu Max Jiang
Chiyu 'Max' Jiang (蒋驰宇)

TLM / Staff Research Scientist, Waymo Research
Generative Modeling for Autonomous Vehicles

Bio

I am currently a TLM/Staff Research Scientst at Waymo (formerly the Google self-driving car project), where I work on Machine Learning algorithms for autonomous vehicles. My research interest is in building foundational generative models that serve the entire self driving stack, from perception, behavior prediction to planning and simulation.

I received a Ph.D. from UC Berkeley in 2020. I worked on 3D Computer Vision / Geometric Deep Learning algorithms, and have first-author publications in top CV/ML conferences (CVPR, ICCV, NeurIPS, ICLR). During my Ph.D. I had the pleasure of collaborating with Matthias Niessner (TUM), Tom Funkhouser (Google), Leonidas Guibas (Stanford), Andrea Tagliasacchi (Google Brain), Anima Anandkumar (CalTech, NVIDIA) and Prabhat (LBNL), among other amazing researchers in this field. I was advised by Philip Marcus, and I have worked as interns and student researchers at Google AI and Lawrence Berkeley National Lab.

News

  • [06/2023] New! Three papers accepted to and presented at CVPR 2023!
  • [09/2022] Our paper, Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining, has been accepted to ECCV 2022!
  • [09/2021] Our paper, Shape-As-Points, has been accepted to NeurIPS 2021 as an Oral paper!
  • [01/2021] I have started at Waymo as a research scientist working on 3D perception research.
  • [06/2020] Our recent work, ShapeFlow, has been accepted to NeurIPS 2020 for publication (spotlight).
  • [06/2020] Our recent work, MeshfreeFlowNet, has been nominated for the Best Student Paper Award!
See More

  • [06/2020] I started the position of Senior Applied Research Scientist at Cruise, working on 3D Computer Vision for self-driving cars.
  • [06/2020] Our recent work, MeshfreeFlowNet, has been selected for publication at SC20!
  • [03/2020] Two papers accepted to CVPR 2020! Check out our papers on local implicit grid representations for 3D scenes, and adversarial texture optimization from RGB-D scans.
  • [07/2019] Our recent paper on Deep Differentiable Simplex Layer has been accepted to ICCV 2019 conference!
  • [05/2019] I will be interning in Machine Perception @ Google Research in summer 2019 as a Ph.D research intern.
  • [12/2018] My work on Spherical CNNs on Unstructred Grids has been chosen for an oral presentation at the AGU (Americal Geophysics Union).
  • Two of my papers have been accepted to the ICLR 2019 conference!
  • [06/2018] I am interning this summer at the Data Analytics group in NERSC, Lawrence Berkeley National Labratory, working with Prabhat and Karthik Karshinath on new Deep Learning methodologies for Climate Science.
  • [03/2018] I am invited to visit Center for Nonlinear Studies at Los Alamos National Labratory, and to present my work on 3D deep learning.
  • [01/2018] I made an oral presentation of my work on Aerodynamics Optimization using Deep Learning at Physics Informed Machine Learning.

Experiences

Waymo | Mountain View, CA

  • (01/2011 - Present) Tech Lead Manager / Staff Research Scientist, Waymo Research
    • Generative Models for Autonomous Vehicles (Perception, Prediction, Planning, Simulation).

Cruise | San Francisco, CA

  • (06/2020 - 01/2021) Senior Applied Research Scientist, Computer Vision
    • Successfully delivered and deployed a new generation 3D object detection solution, leading to a significant functional and latency improvement, resulting in increased safety of the car.
    • Led and coordinated cross-team collaboration for deployment and performance optimization.

Google AI | Mountain View, CA

  • (05/2019 - 03/2020) Research Intern / Student Researcher
    • Developed novel learning based implicit 3D geometry representation for large-scale scene reconstruction from point clouds (Local Implicit Grid - CVPR 2020).
    • Collaborated on a project for generating enhanced texture for scanned 3D models (Adversarial Texture Optimization - CVPR 2020).
    • Proficient with Google internal infrastructure and TensorFlow for ML development, and Apache Beam for massive data processing and ML inference workflows.
    • Initiated and coordinated internal and external collaborations with research partners.

Lawrence Berekely National Lab | Berkeley, CA

  • (05/2018 - 05/2020) Research Intern / Student Researcher

Professional Service

Reviewer for ICCV, AAAI, CVPR, ECCV, NeurIPS, ICLR, SIGGRAPH.

Publications

 MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2023, Highlight, 2.6% acceptance rate)
Chiyu "Max" Jiang*, Andre Cornman*, Cheolho Park, Ben Sapp, Yin Zhou, Dragomir Anguelov (*equal contributions)

OpenScene: 3D Scene Understanding with Open Vocabularies
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2023)
Songyou Peng, Kyle Genova, Chiyu "Max" Jiang, Andrea Tagliasacchi, Marc Pollefeys, Thomas Funkhouser

NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2023)
Congyue Deng, Chiyu "Max" Jiang, Charles R. Qi, Xinchen Yan, Yin Zhou, Leonidas Guibas, Dragomir Anguelov

Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining
European Conference on Computer Vision (ECCV, 2022)
Chiyu "Max" Jiang, Mahyar Najibi, Charles R. Qi, Yin Zhou, Dragomir Anguelov

Shape-As-Points: A Differentiable Poisson Solver
Neural Information Processing Systems (NeurIPS 2021, Oral)
Songyou Peng, Chiyu "Max" Jiang*, Yiyi Liao*, Michael Niemeyer, Marc Pollefeys, Andreas Geiger (* corresponding authors)

ShapeFlow: Learnable Deformations Among 3D Shapes
Neural Information Processing Systems (NeurIPS 2020, Spotlight)
Chiyu "Max" Jiang*, Jingwei Huang*, Andrea Tagliasacchi, Leonidas Guibas

MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework
International Conference for High Performance Computing, Networking, Storage and Analysis (SC20, Best Student Paper nomination)
Chiyu "Max" Jiang*, Soheil Esmaeilzadeh*, Kamyar Azizzadenesheli, Karthik Kashinath, Mustafa Mustafa, Hamdi Tchelepi, Philip Marcus, Prabhat, Anima Anandkumar

Local Implicit Grid Representations for 3D Scenes
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)
Chiyu "Max" Jiang, Avneesh Sud, Ameesh Makadia, Jingwei Huang, Matthias Niessner, Tom Funkhouser

Adversarial Texture Optimization from RGB-D Scans
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)
Jingwei Huang, Justus Thies, Angela Dai, Abhijit Kundu, Chiyu "Max" Jiang, Leonidas Guibas, Matthias Niessner, Tom Funkhouser

DDSL: Deep Differentiable Simplex Layer for Learning Geometric Signals
Proceedings of the IEEE International Conference on Computer Vision (2019)
Chiyu "Max" Jiang*, Dana Lansigan*, Philip Marcus, Matthias Niessner

Spherical CNNs on Unstructured Grids
International Conference on Learning Representations (2019)
Chiyu "Max" Jiang, Jingwei Huang, Karthik Kashinath, Prabhat, Philip Marcus, Matthias Niessner

Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation
International Conference on Learning Representations (2019)
Chiyu "Max" Jiang, Dequan Wang, Jingwei Huang, Philip Marcus, Matthias Niessner

Leveraging Bayesian Analysis To Improve Reduced Order Models
Journal of Computational Physics (2019): 280-297.
B.T. Nadiga, Chiyu Max Jiang, Daniel Livscu

Finding the optimal shape of the leading-and-trailing car of a high-speed train using design-by-morphing
Computational Mechanics (2017): 1-23.
Sahuck Oh, Chung-Hsiang Jiang, Chiyu "Max" Jiang, Philip Marcus

Hierarchical Detail Enhancing Mesh-Based Shape Generation with 3D Generative Adversarial Network
Chiyu "Max" Jiang, Philip Marcus

Other Select Projects

Morphing of Genus-Zero Shapes using Spherical Parameterization  
Chiyu "Max" Jiang, Philip Marcus