Josh Tenenbaum

70

Papers

4,130

Total Citations

Papers (70)

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

NeurIPS 2016arXiv

Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation

NeurIPS 2016arXiv

MarrNet: 3D Shape Reconstruction via 2.5D Sketches

NeurIPS 2017arXiv

Video Language Planning

Self-Supervised Intrinsic Image Decomposition

NeurIPS 2017arXiv

Shape and Material from Sound

Probing the Compositionality of Intuitive Functions

Sampling for Bayesian Program Learning

Softstar: Heuristic-Guided Probabilistic Inference

Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning

Compositional Image Decomposition with Diffusion Models

LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery

Improving Factuality and Reasoning in Language Models through Multiagent Debate

Learning Iterative Reasoning through Energy Diffusion

Potential Based Diffusion Motion Planning

ContPhy: Continuum Physical Concept Learning and Reasoning from Videos

Learning to See Physics via Visual De-animation

Unsupervised Learning by Program Synthesis

Deep Convolutional Inverse Graphics Network

NeurIPS 2015arXiv

Learning Compositional Rules via Neural Program Synthesis

Program Synthesis with Pragmatic Communication

Online Bayesian Goal Inference for Boundedly Rational Planning Agents

Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language

A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics

Grammar-Based Grounded Lexicon Learning

Learning Signal-Agnostic Manifolds of Neural Fields

3DP3: 3D Scene Perception via Probabilistic Programming

Unsupervised Learning of Compositional Energy Concepts

Noether Networks: meta-learning useful conserved quantities

PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning

Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering

Learning to Compose Visual Relations

Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning

Learning Neural Acoustic Fields

Communicating Natural Programs to Humans and Machines

3D Concept Grounding on Neural Fields

HandMeThat: Human-Robot Communication in Physical and Social Environments

Drawing out of Distribution with Neuro-Symbolic Generative Models

Learning Physical Dynamics with Subequivariant Graph Neural Networks

When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment

PDSketch: Integrated Domain Programming, Learning, and Planning

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

Learning Universal Policies via Text-Guided Video Generation

Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision

Inferring the Future by Imagining the Past

Compositional Foundation Models for Hierarchical Planning

What’s Left? Concept Grounding with Logic-Enhanced Foundation Models

DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models

Human spatiotemporal pattern learning as probabilistic program synthesis

What Planning Problems Can A Relational Neural Network Solve?

Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties

Risk and Regret of Hierarchical Bayesian Learners

Learning to Share and Hide Intentions using Information Regularization

Learning to Reconstruct Shapes from Unseen Classes

Learning to Exploit Stability for 3D Scene Parsing

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

3D-Aware Scene Manipulation via Inverse Graphics

Learning to Infer Graphics Programs from Hand-Drawn Images

Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction

End-to-End Differentiable Physics for Learning and Control

Visual Object Networks: Image Generation with Disentangled 3D Representations

Flexible neural representation for physics prediction

Write, Execute, Assess: Program Synthesis with a REPL

Finding Friend and Foe in Multi-Agent Games

ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models

Visual Concept-Metaconcept Learning

Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations

Learning abstract structure for drawing by efficient motor program induction

Learning Physical Graph Representations from Visual Scenes

Multi-Plane Program Induction with 3D Box Priors