Jiajun Wu

verfied profile

∙ 0 followers
MIT ∙ Stanford University

Visiting Faculty Researcher, Google Research

Featured Co-authors

Sergey Levine
210 publications
Li Fei-Fei
99 publications
Joshua B. Tenenbaum
80 publications
Pushmeet Kohli
79 publications
Antonio Torralba
74 publications
Chelsea Finn
66 publications
Bo Liu
57 publications
Xiao Liu
55 publications
Kevin Murphy
51 publications
William T. Freeman
45 publications
Simon S. Du
45 publications

Perspective Plane Program Induction from a Single Image

We study the inverse graphics problem of inferring a holistic representa...
06/25/2020 ∙ by Yikai Li, et al. ∙ 8 ∙ share

read it
Learning Physical Graph Representations from Visual Scenes

Convolutional Neural Networks (CNNs) have proved exceptional at learning...
06/22/2020 ∙ by Daniel M. Bear, et al. ∙ 10 ∙ share

read it
When is Particle Filtering Efficient for POMDP Sequential Planning?

Particle filtering is a popular method for inferring latent states in st...
06/10/2020 ∙ by Simon S. Du, et al. ∙ 1 ∙ share

read it
Data Represention for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks

Deep neural networks (DNNs) have been applied to address various wireles...
05/18/2020 ∙ by Chengjian Sun, et al. ∙ 0 ∙ share

read it
Visual Grounding of Learned Physical Models

Humans intuitively recognize objects' physical properties and predict th...
04/28/2020 ∙ by Yunzhu Li, et al. ∙ 2 ∙ share

read it
Visual Concept-Metaconcept Learning

Humans reason with concepts and metaconcepts: we recognize red and green...
02/04/2020 ∙ by Chi Han, et al. ∙ 1 ∙ share

read it
Look, Listen, and Act: Towards Audio-Visual Embodied Navigation

A crucial aspect of mobile intelligent agents is their ability to integr...
12/25/2019 ∙ by Chuang Gan, et al. ∙ 2 ∙ share

read it
Accurate Vision-based Manipulation through Contact Reasoning

Planning contact interactions is one of the core challenges of many robo...
11/08/2019 ∙ by Alina Kloss, et al. ∙ 18 ∙ share

read it
Proactive Optimization with Unsupervised Learning

Proactive resource allocation, say proactive caching at wireless edge, h...
10/29/2019 ∙ by Jiajun Wu, et al. ∙ 0 ∙ share

read it
Entity Abstraction in Visual Model-Based Reinforcement Learning

This paper tests the hypothesis that modeling a scene in terms of entiti...
10/28/2019 ∙ by Rishi Veerapaneni, et al. ∙ 33 ∙ share

read it
Learning Compositional Koopman Operators for Model-Based Control

Finding an embedding space for a linear approximation of a nonlinear dyn...
10/18/2019 ∙ by Yunzhu Li, et al. ∙ 0 ∙ share

read it
CLEVRER: CoLlision Events for Video REpresentation and Reasoning

The ability to reason about temporal and causal events from videos lies ...
10/03/2019 ∙ by Kexin Yi, et al. ∙ 12 ∙ share

read it
Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs

We present the DualSMC network that solves continuous POMDPs by learning...
09/28/2019 ∙ by Yunbo Wang, et al. ∙ 15 ∙ share

read it
Program-Guided Image Manipulators

Humans are capable of building holistic representations for images at va...
09/04/2019 ∙ by Jiayuan Mao, et al. ∙ 4 ∙ share

read it
Neurally-Guided Structure Inference

Most structure inference methods either rely on exhaustive search or are...
06/17/2019 ∙ by Sidi Lu, et al. ∙ 2 ∙ share

read it
DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions

We study the problem of learning physical object representations for rob...
06/10/2019 ∙ by Zhenjia Xu, et al. ∙ 13 ∙ share

read it
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that lear...
04/26/2019 ∙ by Jiayuan Mao, et al. ∙ 12 ∙ share

read it
Combining Physical Simulators and Object-Based Networks for Control

Physics engines play an important role in robot planning and control; ho...
04/13/2019 ∙ by Anurag Ajay, et al. ∙ 0 ∙ share

read it
Unsupervised Discovery of Parts, Structure, and Dynamics

Humans easily recognize object parts and their hierarchical structure by...
03/12/2019 ∙ by Zhenjia Xu, et al. ∙ 12 ∙ share

read it
Stochastic Prediction of Multi-Agent Interactions from Partial Observations

We present a method that learns to integrate temporal information, from ...
02/25/2019 ∙ by Chen Sun, et al. ∙ 8 ∙ share

read it
Learning to Infer and Execute 3D Shape Programs

Human perception of 3D shapes goes beyond reconstructing them as a set o...
01/09/2019 ∙ by Yonglong Tian, et al. ∙ 6 ∙ share

read it
Learning to Reconstruct Shapes from Unseen Classes

From a single image, humans are able to perceive the full 3D shape of an...
12/28/2018 ∙ by Xiuming Zhang, et al. ∙ 0 ∙ share

read it
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning

Object-based factorizations provide a useful level of abstraction for in...
12/28/2018 ∙ by Michael Janner, et al. ∙ 14 ∙ share

read it
Visual Object Networks: Image Generation with Disentangled 3D Representation

Recent progress in deep generative models has led to tremendous breakthr...
12/06/2018 ∙ by Jun-Yan Zhu, et al. ∙ 8 ∙ share

read it
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding

We marry two powerful ideas: deep representation learning for visual rec...
10/04/2018 ∙ by Kexin Yi, et al. ∙ 0 ∙ share

read it
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids

Real-life control tasks involve matter of various substances---rigid or ...
10/03/2018 ∙ by Yunzhu Li, et al. ∙ 2 ∙ share

read it
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics

Physical simulators have been widely used in robot planning and control....
10/02/2018 ∙ by Yuanming Hu, et al. ∙ 2 ∙ share

read it
Propagation Networks for Model-Based Control Under Partial Observation

There has been an increasing interest in learning dynamics simulators fo...
09/28/2018 ∙ by Yunzhu Li, et al. ∙ 4 ∙ share

read it
MoSculp: Interactive Visualization of Shape and Time

We present a system that allows users to visualize complex human motion ...
09/14/2018 ∙ by Xiuming Zhang, et al. ∙ 0 ∙ share

read it
Physical Primitive Decomposition

Objects are made of parts, each with distinct geometry, physics, functio...
09/13/2018 ∙ by Zhijian Liu, et al. ∙ 4 ∙ share

read it
Learning Shape Priors for Single-View 3D Completion and Reconstruction

The problem of single-view 3D shape completion or reconstruction is chal...
09/13/2018 ∙ by Jiajun Wu, et al. ∙ 0 ∙ share

read it
Seeing Tree Structure from Vibration

Humans recognize object structure from both their appearance and motion;...
09/13/2018 ∙ by Tianfan Xue, et al. ∙ 4 ∙ share

read it
3D-Aware Scene Manipulation via Inverse Graphics

We aim to obtain an interpretable, expressive and disentangled scene rep...
08/28/2018 ∙ by Shunyu Yao, et al. ∙ 0 ∙ share

read it
3D Shape Perception from Monocular Vision, Touch, and Shape Priors

Perceiving accurate 3D object shape is important for robots to interact ...
08/09/2018 ∙ by Shaoxiong Wang, et al. ∙ 8 ∙ share

read it
Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing

An efficient, generalizable physical simulator with universal uncertaint...
08/09/2018 ∙ by Anurag Ajay, et al. ∙ 0 ∙ share

read it
Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks

We study the problem of synthesizing a number of likely future frames fr...
07/24/2018 ∙ by Tianfan Xue, et al. ∙ 2 ∙ share

read it
Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks

We propose a framework for the completely unsupervised learning of laten...
07/24/2018 ∙ by David Zheng, et al. ∙ 0 ∙ share

read it
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

We study 3D shape modeling from a single image and make contributions to...
04/12/2018 ∙ by Xingyuan Sun, et al. ∙ 2 ∙ share

read it
3D Interpreter Networks for Viewer-Centered Wireframe Modeling

Understanding 3D object structure from a single image is an important bu...
04/03/2018 ∙ by Jiajun Wu, et al. ∙ 0 ∙ share

read it
Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning

The sound of crashing waves, the roar of fast-moving cars -- sound conve...
12/20/2017 ∙ by Andrew Owens, et al. ∙ 0 ∙ share

read it
Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification

Recently, substantial research effort has focused on how to apply CNNs o...
11/27/2017 ∙ by Xiang Long, et al. ∙ 0 ∙ share

read it
Video Enhancement with Task-Oriented Flow

Many video processing algorithms rely on optical flow to register differ...
11/24/2017 ∙ by Tianfan Xue, et al. ∙ 0 ∙ share

read it
Self-Supervised Intrinsic Image Decomposition

Intrinsic decomposition from a single image is a highly challenging task...
11/10/2017 ∙ by Michael Janner, et al. ∙ 0 ∙ share

read it
MarrNet: 3D Shape Reconstruction via 2.5D Sketches

3D object reconstruction from a single image is a highly under-determine...
11/08/2017 ∙ by Jiajun Wu, et al. ∙ 0 ∙ share

read it
Deep Multi-Modal Image Correspondence Learning

Inference of correspondences between images from different modalities is...
12/05/2016 ∙ by Chen Liu, et al. ∙ 0 ∙ share

read it
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

We study the problem of 3D object generation. We propose a novel framewo...
10/24/2016 ∙ by Jiajun Wu, et al. ∙ 0 ∙ share

read it
Ambient Sound Provides Supervision for Visual Learning

The sound of crashing waves, the roar of fast-moving cars -- sound conve...
08/25/2016 ∙ by Andrew Owens, et al. ∙ 0 ∙ share

read it
Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

We study the problem of synthesizing a number of likely future frames fr...
07/09/2016 ∙ by Tianfan Xue, et al. ∙ 0 ∙ share

read it