J
Jiajun Wu
Researcher at Stanford University
Publications - 216
Citations - 13655
Jiajun Wu is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Object (computer science). The author has an hindex of 48, co-authored 169 publications receiving 9618 citations. Previous affiliations of Jiajun Wu include Massachusetts Institute of Technology & Princeton University.
Papers
More filters
Journal ArticleDOI
See, feel, act: Hierarchical learning for complex manipulation skills with multisensory fusion
TL;DR: This work proposes a methodology to emulate hierarchical reasoning and multisensory fusion in a robot that learns to play Jenga, a complex game that requires physical interaction to be played effectively.
Proceedings Article
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
TL;DR: Neuro-Symbolic Concept Learner (NS-CL) as discussed by the authors is a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, the model learns by simply looking at images and reading paired questions and answers.
Posted Content
MarrNet: 3D Shape Reconstruction via 2.5D Sketches
TL;DR: MarrNet as discussed by the authors proposes an end-to-end trainable model that sequentially estimates 2.5D sketches and 3D object shapes from a single image, which is trained on synthetic data with ground truth 3D information.
Proceedings Article
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
TL;DR: This study helps lay the foundation for robot learning of dynamic scenes with particle-based representations, and demonstrates robots achieving complex manipulation tasks using the learned simulator, such as manipulating fluids and deformable foam.
Proceedings ArticleDOI
Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
Anurag Ajay,Jiajun Wu,Nima Fazeli,Maria Bauza,Leslie Pack Kaelbling,Joshua B. Tenenbaum,Alberto Rodriguez +6 more
TL;DR: This paper builds an efficient, generalizable physical simulator with universal uncertainty estimates for two scenarios, planar pushing and ball bouncing, by augmenting an analytical rigid-body simulator with a neural network that learns to model uncertainty as residuals.