Jiajun Wu

Orcid: 0000-0002-4176-343X

Affiliations:
  • Stanford University, Stanford, CA, USA
  • Massachusetts Institute of Technology, CSAIL, Cambridge, MA, USA (Ph.D.)


According to our database1, Jiajun Wu authored at least 253 papers between 2012 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
An Eulerian Vortex Method on Flow Maps.
ACM Trans. Graph., December, 2024

Unsupervised 3D Scene Representation Learning via Movable Object Inference.
Trans. Mach. Learn. Res., 2024

RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks.
Int. J. Robotics Res., 2024

The Scene Language: Representing Scenes with Programs, Words, and Embeddings.
CoRR, 2024

Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies.
CoRR, 2024

Generalizable Humanoid Manipulation with Improved 3D Diffusion Policies.
CoRR, 2024

Automated Creation of Digital Cousins for Robust Policy Learning.
CoRR, 2024

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making.
CoRR, 2024

Don't Cut Corners: Exact Conditions for Modularity in Biologically Inspired Representations.
CoRR, 2024

MARPLE: A Benchmark for Long-Horizon Inference.
CoRR, 2024

What Makes a Maze Look Like a Maze?
CoRR, 2024

View-Invariant Policy Learning via Zero-Shot Novel View Synthesis.
CoRR, 2024

RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing.
CoRR, 2024

WonderWorld: Interactive 3D Scene Generation from a Single Image.
CoRR, 2024

TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction.
CoRR, 2024

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation.
CoRR, 2024

Evaluating Real-World Robot Manipulation Policies in Simulation.
CoRR, 2024

Text-Based Reasoning About Vector Graphics.
CoRR, 2024

BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1, 000 Everyday Activities and Realistic Simulation.
CoRR, 2024

Unsupervised Discovery of Object-Centric Neural Fields.
CoRR, 2024

Physical scene understanding.
AI Mag., 2024

DiffSound: Differentiable Modal Sound Rendering and Inverse Rendering for Diverse Inference Tasks.
Proceedings of the ACM SIGGRAPH 2024 Conference Papers, 2024

D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning.
RLJ, 2024

Efficient imitation learning with conservative world models.
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024

Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Learning to Design 3D Printable Adaptations on Everyday Objects for Robot Manipulation.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Physically Grounded Vision-Language Models for Robotic Manipulation.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Learning Planning Abstractions from Language.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Language-Informed Visual Concept Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Patched Denoising Diffusion Models For High-Resolution Image Synthesis.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Neural Polynomial Gabor Fields for Macro Motion Analysis.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians.
Proceedings of the Computer Vision - ECCV 2024, 2024

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation.
Proceedings of the Computer Vision - ECCV 2024, 2024

3D Congealing: 3D-Aware Image Alignment in the Wild.
Proceedings of the Computer Vision - ECCV 2024, 2024

Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos.
Proceedings of the Computer Vision - ECCV 2024, 2024

Controllable Human-Object Interaction Synthesis.
Proceedings of the Computer Vision - ECCV 2024, 2024

WonderJourney: Going from Anywhere to Everywhere.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Holodeck: Language Guided Generation of 3D Embodied AI Environments.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

ULIP-2: Towards Scalable Multimodal Pre-Training for 3D Understanding.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Hearing Anything Anywhere.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Learning the 3D Fauna of the Web.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

CityPulse: Fine-Grained Assessment of Urban Change with Street View Time Series.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Partial-View Object View Synthesis via Filtering Inversion.
Proceedings of the International Conference on 3D Vision, 2024

2023
Editing Motion Graphics Video via Motion Vectorization and Transformation.
ACM Trans. Graph., December, 2023

Object Motion Guided Human Motion Synthesis.
ACM Trans. Graph., December, 2023

Fluid Simulation on Neural Flow Maps.
ACM Trans. Graph., December, 2023

Ego-Body Pose Estimation via Ego-Head Pose Estimation.
AI Matters, June, 2023

Differentiable Physics Simulation of Dynamics-Augmented Neural Objects.
IEEE Robotics Autom. Lett., May, 2023

Neurosymbolic Models for Computer Graphics.
Comput. Graph. Forum, May, 2023

Learning Object-Centric Neural Scattering Functions for Free-viewpoint Relighting and Scene Composition.
Trans. Mach. Learn. Res., 2023

Unsupervised Discovery and Composition of Object Light Fields.
Trans. Mach. Learn. Res., 2023

DisCo: Improving Compositional Generalization in Visual Reasoning through Distribution Coverage.
Trans. Mach. Learn. Res., 2023

Ponymation: Learning 3D Animal Motions from Unlabeled Online Videos.
CoRR, 2023

Foundation Models in Robotics: Applications, Challenges, and the Future.
CoRR, 2023

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Real Image.
CoRR, 2023

Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI.
CoRR, 2023

D<sup>3</sup>Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Robotic Manipulation.
CoRR, 2023

PyPose v0.6: The Imperative Programming Interface for Robotics.
CoRR, 2023

Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations.
CoRR, 2023

HomE: Homography-Equivariant Video Representation Learning.
CoRR, 2023

The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects.
CoRR, 2023

An Extensible Multimodal Multi-task Object Dataset with Materials.
CoRR, 2023

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding.
CoRR, 2023

Partial-View Object View Synthesis via Filtered Inversion.
CoRR, 2023

Physically Plausible Animation of Human Upper Body from a Single Image.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

Dynamic-Resolution Model Learning for Object Pile Manipulation.
Proceedings of the Robotics: Science and Systems XIX, Daegu, 2023

Inferring Hybrid Neural Fluid Fields from Videos.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SoundCam: A Dataset for Finding Humans Using Room Acoustics.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Holistic Evaluation of Text-to-Image Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Are These the Same Apple? Comparing Images Based on Object Intrinsics.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

What's Left? Concept Grounding with Logic-Enhanced Foundation Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Disentanglement via Latent Quantization.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Siamese Masked Autoencoders.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Model-Based Control with Sparse Neural Dynamics.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Benchmarking Rigid Body Contact Models.
Proceedings of the Learning for Dynamics and Control Conference, 2023

Primitive Skill-Based Robot Learning from Human Evaluative Feedback.
IROS, 2023

Task-Driven Graph Attention for Hierarchical Relational Object Navigation.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

STAP: Sequencing Task-Agnostic Policies.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Modeling Dynamic Environments with Scene Graph Memory.
Proceedings of the International Conference on Machine Learning, 2023

Motion Question Answering via Modular Motion Programs.
Proceedings of the International Conference on Machine Learning, 2023

Programmatically Grounded, Compositionally Generalizable Robotic Manipulation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

A Control-Centric Benchmark for Video Prediction.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

An Extensible Multi-modal Multi-task Object Dataset with Materials.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

MaskViT: Masked Visual Pre-Training for Video Prediction.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Learning Vortex Dynamics for Fluid Inference and Prediction.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Rendering Humans from Object-Occluded Monocular Videos.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

VQ3D: Learning a 3D-Aware Generative Model on ImageNet.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Tree-Structured Shading Decomposition.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Can Visual Scratchpads With Diagrammatic Abstractions Augment LLM Reasoning?
Proceedings of the Proceedings on "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops, 2023

Seeing a Rose in Five Thousand Ways.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Accidental Light Probes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023


Multi-Object Manipulation via Object-Centric Neural Scattering Functions.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

3D Neural Field Generation Using Triplane Diffusion.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Putting People in Their Place: Affordance-Aware Human Insertion into Scenes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

The Object Folder Benchmark : Multisensory Learning with Neural and Real Objects.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

REALIMPACT: A Dataset of Impact Sound Fields for Real Objects.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

CIRCLE: Capture In Rich Contextual Environments.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities.
Proceedings of the Conference on Robot Learning, 2023

Compositional Diffusion-Based Continuous Constraint Solvers.
Proceedings of the Conference on Robot Learning, 2023

Learning Sequential Acquisition Policies for Robot-Assisted Feeding.
Proceedings of the Conference on Robot Learning, 2023

RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools.
Proceedings of the Conference on Robot Learning, 2023

Composable Part-Based Manipulation.
Proceedings of the Conference on Robot Learning, 2023

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models.
Proceedings of the Conference on Robot Learning, 2023

Learning to Design and Use Tools for Robotic Manipulation.
Proceedings of the Conference on Robot Learning, 2023

Intuitions about physical scenes and objects in Virtual Reality (VR).
Proceedings of the 45th Annual Meeting of the Cognitive Science Society, 2023

Quantifying the Effect of Visual Impairments on Daily Activities in Virtual, Interactive Environments.
Proceedings of the 45th Annual Meeting of the Cognitive Science Society, 2023

Learning Rational Subgoals from Demonstrations and Instructions.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
ULIP: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding.
CoRR, 2022

TAPS: Task-Agnostic Policy Sequencing.
CoRR, 2022

Retrospectives on the Embodied AI Workshop.
CoRR, 2022

PyPose: A Library for Robot Learning with Physics-based Optimization.
CoRR, 2022

BEHAVIOR in Habitat 2.0: Simulator-Independent Logical Task Description for Benchmarking Embodied AI Agents.
CoRR, 2022

Scene Synthesis from Human Motion.
Proceedings of the SIGGRAPH Asia 2022 Conference Papers, 2022

RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks.
Proceedings of the Robotics: Science and Systems XVIII, New York City, NY, USA, June 27, 2022

IKEA-Manual: Seeing Shape Assembly Step by Step.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Interaction Modeling with Multiplex Attention.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

CLEVRER-Humans: Describing Physical and Causal Events the Human Way.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Geoclidean: Few-Shot Generalization in Euclidean Geometry.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Unsupervised Learning of Shape Programs with Repeatable Implicit Parts.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Sparse and Local Networks for Hypergraph Reasoning.
Proceedings of the Learning on Graphs Conference, 2022

Unsupervised Discovery of Object Radiance Fields.
Proceedings of the Tenth International Conference on Learning Representations, 2022

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Vision-Based Manipulators Need to Also See from Their Hands.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Video Extrapolation in Space and Time.
Proceedings of the Computer Vision - ECCV 2022, 2022

Translating a Visual LEGO Manual to a Machine-Executable Plan.
Proceedings of the Computer Vision - ECCV 2022, 2022

Unsupervised Segmentation in Real-World Images via Spelke Object Inference.
Proceedings of the Computer Vision - ECCV 2022, 2022

Rotationally Equivariant 3D Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Programmatic Concept Learning for Human Motion Description and Synthesis.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Revisiting the "Video" in Video-Language Understanding.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

A Dual Representation Framework for Robot Learning with Human Guidance.
Proceedings of the Conference on Robot Learning, 2022

See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation.
Proceedings of the Conference on Robot Learning, 2022


2021
SDEdit: Image Synthesis and Editing with Stochastic Differential Equations.
CoRR, 2021

Learning to see the physical world.
AI Matters, 2021

When is particle filtering efficient for planning in partially observed linear dynamical systems?
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

DASH: Modularized Human Manipulation Simulation with Vision and Language for Embodied AI.
Proceedings of the SCA '21: The ACM SIGGRAPH / Eurographics Symposium on Computer Animation, 2021

Grammar-Based Grounded Lexicon Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Temporal and Object Quantification Networks.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

Unsupervised Discovery of 3D Physical Objects from Video.
Proceedings of the 9th International Conference on Learning Representations, 2021

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning.
Proceedings of the 9th International Conference on Learning Representations, 2021

3D Shape Generation and Completion through Point-Voxel Diffusion.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Learning Temporal Dynamics from Cycles in Narrated Video.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Neural Radiance Flow for 4D View Synthesis and Video Processing.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

De-Rendering the World's Revolutionary Artefacts.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Repopulating Street Scenes.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Hierarchical Motion Understanding via Motion Programs.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Single-Shot Scene Reconstruction.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

DiffImpact: Differentiable Rendering and Identification of Impact Sounds.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

Language-Mediated, Object-Centric Representation Learning.
Proceedings of the Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, 2021

Augmenting Policy Learning with Routines Discovered from a Single Demonstration.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Augmenting Policy Learning with Routines Discovered from a Demonstration.
CoRR, 2020

Object-Centric Diagnosis of Visual Reasoning.
CoRR, 2020

Object-Centric Neural Scene Rendering.
CoRR, 2020

Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection.
CoRR, 2020

Unsupervised Discovery of 3D Physical Objects from Video.
CoRR, 2020

When is Particle Filtering Efficient for POMDP Sequential Planning?
CoRR, 2020

Learning Generative Models of 3D Structures.
Comput. Graph. Forum, 2020

Multi-Plane Program Induction with 3D Box Priors.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning Physical Graph Representations from Visual Scenes.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020

Accurate Vision-based Manipulation through Contact Reasoning.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Look, Listen, and Act: Towards Audio-Visual Embodied Navigation.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Visual Grounding of Learned Physical Models.
Proceedings of the 37th International Conference on Machine Learning, 2020

Deep Audio Priors Emerge From Harmonic Convolutional Networks.
Proceedings of the 8th International Conference on Learning Representations, 2020

CLEVRER: Collision Events for Video Representation and Reasoning.
Proceedings of the 8th International Conference on Learning Representations, 2020

Learning Compositional Koopman Operators for Model-Based Control.
Proceedings of the 8th International Conference on Learning Representations, 2020

Probabilistic Video Prediction From Noisy Data With a Posterior Confidence.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

End-to-End Optimization of Scene Layout.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Perspective Plane Program Induction From a Single Image.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Learning 3D Dynamic Scene Representations for Robot Manipulation.
Proceedings of the 4th Conference on Robot Learning, 2020

The fine structure of surprise in intuitive physics: when, why, and how much?
Proceedings of the 42th Annual Meeting of the Cognitive Science Society, 2020

2019
See, feel, act: Hierarchical learning for complex manipulation skills with multisensory fusion.
Sci. Robotics, 2019

Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks.
IEEE Trans. Pattern Anal. Mach. Intell., 2019

Video Enhancement with Task-Oriented Flow.
Int. J. Comput. Vis., 2019

Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs.
CoRR, 2019

DensePhysNet: Learning Dense Physical Object Representations Via Multi-Step Dynamic Interactions.
Proceedings of the Robotics: Science and Systems XV, 2019

Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Visual Concept-Metaconcept Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Propagation Networks for Model-Based Control Under Partial Observation.
Proceedings of the International Conference on Robotics and Automation, 2019

ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics.
Proceedings of the International Conference on Robotics and Automation, 2019

Combining Physical Simulators and Object-Based Networks for Control.
Proceedings of the International Conference on Robotics and Automation, 2019

Neurally-Guided Structure Inference.
Proceedings of the 36th International Conference on Machine Learning, 2019

Unsupervised Discovery of Parts, Structure, and Dynamics.
Proceedings of the 7th International Conference on Learning Representations, 2019

Learning to Infer and Execute 3D Shape Programs.
Proceedings of the 7th International Conference on Learning Representations, 2019

Stochastic Prediction of Multi-Agent Interactions from Partial Observations.
Proceedings of the 7th International Conference on Learning Representations, 2019

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision.
Proceedings of the 7th International Conference on Learning Representations, 2019

Learning to Describe Scenes with Programs.
Proceedings of the 7th International Conference on Learning Representations, 2019

Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids.
Proceedings of the 7th International Conference on Learning Representations, 2019

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning.
Proceedings of the 7th International Conference on Learning Representations, 2019

Program-Guided Image Manipulators.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Entity Abstraction in Visual Model-Based Reinforcement Learning.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

Real-time inference of physical properties in dynamic scenes.
Proceedings of the 41th Annual Meeting of the Cognitive Science Society, 2019

2018
3D Interpreter Networks for Viewer-Centered Wireframe Modeling.
Int. J. Comput. Vis., 2018

Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning.
Int. J. Comput. Vis., 2018

Visual Object Networks: Image Generation with Disentangled 3D Representation.
CoRR, 2018

MoSculp: Interactive Visualization of Shape and Time.
Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology, 2018

Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks.
Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, 2018

Visual Object Networks: Image Generation with Disentangled 3D Representations.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Learning to Reconstruct Shapes from Unseen Classes.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

3D-Aware Scene Manipulation via Inverse Graphics.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Learning to Exploit Stability for 3D Scene Parsing.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

3D Shape Perception from Monocular Vision, Touch, and Shape Priors.
Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018

Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing.
Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018

Seeing Tree Structure from Vibration.
Proceedings of the Computer Vision - ECCV 2018, 2018

Learning Shape Priors for Single-View 3D Completion And Reconstruction.
Proceedings of the Computer Vision - ECCV 2018, 2018

Physical Primitive Decomposition.
Proceedings of the Computer Vision - ECCV 2018, 2018

Inverting Audio-Visual Simulation for Shape and Material Perception.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017
Shape and Material from Sound.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Self-Supervised Intrinsic Image Decomposition.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

MarrNet: 3D Shape Reconstruction via 2.5D Sketches.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Learning to See Physics via Visual De-animation.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Generative Modeling of Audible Shapes for Object Perception.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Raster-to-Vector: Revisiting Floorplan Transformation.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Synthesizing 3D Shapes via Modeling Multi-view Depth Maps and Silhouettes with Deep Generative Networks.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Neural Scene De-rendering.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2016
Deep Multi-Modal Image Correspondence Learning.
CoRR, 2016

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Ambient Sound Provides Supervision for Visual Learning.
Proceedings of the Computer Vision - ECCV 2016, 2016

Single Image 3D Interpreter Network.
Proceedings of the Computer Vision - ECCV 2016, 2016

A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding.
Proceedings of the 38th Annual Meeting of the Cognitive Science Society, 2016

Physics 101: Learning Physical Object Properties from Unlabeled Videos.
Proceedings of the British Machine Vision Conference 2016, 2016

2015
Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning.
IEEE Trans. Pattern Anal. Mach. Intell., 2015

Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Deep multiple instance learning for image classification and auto-annotation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Harvesting Motion Patterns in Still Images from the Internet.
Proceedings of the 36th Annual Meeting of the Cognitive Science Society, 2014

Reverse Image Segmentation: A High-Level Solution to a Low-Level Task.
Proceedings of the British Machine Vision Conference, 2014

2013
Harvesting Mid-level Visual Concepts from Large-Scale Internet Images.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
A classification approach to coreference in discharge summaries: 2011 i2b2 challenge.
J. Am. Medical Informatics Assoc., 2012

Unsupervised object class discovery via saliency-guided multiple class learning.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012


  Loading...