Sotabase

Career

· Research Scientist, NVIDIA Research2025–
· Research Scientist, Seattle Robotics Lab, NVIDIA Research2022–2025
· Research Intern, Facebook AI Research2020–2020
· Visiting Graduate, Su Lab, University of California, San Diego (UCSD)2019–2019
· Research Intern, Autodesk Research2018–2018
· Research Intern, Adobe Research2017–2017
· Rotation Student, Stanford University2017–2017
· PhD in Computer Science, Stanford University2016–2022
· Exchange Research Scholar, Cornell University2015–2015
· Research Assistant, Shanghai Jiao Tong University2014–2016
· Bachelor of Science, Computer Science, Shanghai Jiao Tong University2012–2016

Publications (50)

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Computer Vision and Pattern Recognition · 2016
16,642
cited
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding
Computer Vision and Pattern Recognition · 2018
851
cited
SAPIEN: A SimulAted Part-Based Interactive ENvironment
Computer Vision and Pattern Recognition · 2020
671
cited
Where2Act: From Pixels to Actions for Articulated 3D Objects
IEEE International Conference on Computer Vision · 2021
222
cited
StructureNet
ACM Transactions on Graphics · 2019
141
cited
VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects
International Conference on Learning Representations · 2021
108
cited
Generative 3D Part Assembly via Dynamic Graph Learning
Neural Information Processing Systems · 2020
103
cited
GIMO: Gaze-Informed Human Motion Prediction in Context
European Conference on Computer Vision · 2022
98
cited
Learning 3D Part Assembly from a Single Image
European Conference on Computer Vision · 2020
80
cited
AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions
European Conference on Computer Vision · 2021
75
cited
O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning
Conference on Robot Learning · 2021
66
cited
SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation With Fine-Grained Geometry
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023
52
cited
StructEdit: Learning Structural Shape Variations
Computer Vision and Pattern Recognition · 2019
47
cited
DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation
ACM Transactions on Graphics · 2020
46
cited
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories
International Conference on Learning Representations · 2020
44
cited
PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
European Conference on Computer Vision · 2020
40
cited
DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry
arXiv.org · 2020
39
cited
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Supplementary Material
2017
38
cited
The AdobeIndoorNav Dataset: Towards Deep Reinforcement Learning based Real-world Indoor Robot Visual Navigation
arXiv.org · 2018
29
cited
DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation
International Conference on Learning Representations · 2022
24
cited
Sotabase
Kaichun Mo | Researcher Profile | Sotabase | Sotabase