Joshua B. Tenenbaum
Massachusetts Institute of Technology
H-index: 137
North America-United States
Description
Joshua B. Tenenbaum, With an exceptional h-index of 137 and a recent h-index of 115 (since 2020), a distinguished researcher at Massachusetts Institute of Technology, specializes in the field of Cognitive science, artificial intelligence, machine learning, computational neuroscience, cognitive psychology.
His recent articles reflect a diverse array of research interests and contributions to the field:
What Planning Problems Can A Relational Neural Network Solve?
Bayesian models of cognition: reverse engineering the mind
WatChat: Explaining perplexing programs by debugging mental models
Systems and methods for reconstructing a scene in three dimensions from a two-dimensional image
Neural amortized inference for nested multi-agent reasoning
Inferring the future by imagining the past
DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models
Intuitive physics as probabilistic inference
Professor Information
University | Massachusetts Institute of Technology |
---|---|
Position | ___ |
Citations(all) | 102796 |
Citations(since 2020) | 56564 |
Cited By | 68673 |
hIndex(all) | 137 |
hIndex(since 2020) | 115 |
i10Index(all) | 499 |
i10Index(since 2020) | 427 |
University Profile Page | Massachusetts Institute of Technology |
Research & Interests List
Cognitive science
artificial intelligence
machine learning
computational neuroscience
cognitive psychology
Top articles of Joshua B. Tenenbaum
What Planning Problems Can A Relational Neural Network Solve?
Goal-conditioned policies are generally understood to be" feed-forward" circuits, in the form of neural networks that map from the current state and the goal specification to the next action to take. However, under what circumstances such a policy can be learned and how efficient the policy will be are not well understood. In this paper, we present a circuit complexity analysis for relational neural networks (such as graph neural networks and transformers) representing policies for planning problems, by drawing connections with serialized goal regression search (S-GRS). We show that there are three general classes of planning problems, in terms of the growth of circuit width and depth as a function of the number of objects and planning horizon, providing constructive proofs. We also illustrate the utility of this analysis for designing neural networks for policy learning.
Authors
Jiayuan Mao,Tomás Lozano-Pérez,Josh Tenenbaum,Leslie Kaelbling
Journal
Advances in Neural Information Processing Systems
Published Date
2024/2/13
Bayesian models of cognition: reverse engineering the mind
Bayesian models of cognition : reverse engineering the mind - WRAP: Warwick Research Archive Portal Skip to content Skip to navigation University of Warwick Study | Research | Business | Alumni | News | About University of Warwick Publications service & WRAP Highlight your research WRAP Home Search WRAP Browse by Warwick Author Browse WRAP by Year Browse WRAP by Subject Browse WRAP by Department Browse WRAP by Funder Browse Theses by Department Publications Service Home Search Publications Service Browse by Warwick Author Browse Publications service by Year Browse Publications service by Subject Browse Publications service by Department Browse Publications service by Funder Help & Advice University of Warwick The Library Login Admin Bayesian models of cognition : reverse engineering the mind Tools + Tools Griffiths, TL and Chater, Nick and Tenenbaum, Joshua B., …
Authors
Thomas L Griffiths,Nick Chater,Joshua B Tenenbaum
Published Date
2024
WatChat: Explaining perplexing programs by debugging mental models
Often, a good explanation for a program's unexpected behavior is a bug in the programmer's code. But sometimes, an even better explanation is a bug in the programmer's mental model of the language they are using. Instead of merely debugging our current code ("giving the programmer a fish"), what if our tools could directly debug our mental models ("teaching the programmer to fish")? In this paper, we apply ideas from computational cognitive science to do exactly that. Given a perplexing program, we use program synthesis techniques to automatically infer potential misconceptions that might cause the user to be surprised by the program's behavior. By analyzing these misconceptions, we provide succinct, useful explanations of the program's behavior. Our methods can even be inverted to synthesize pedagogical example programs for diagnosing and correcting misconceptions in students.
Authors
Kartik Chandra,Tzu-Mao Li,Rachit Nigam,Joshua Tenenbaum,Jonathan Ragan-Kelley
Journal
arXiv preprint arXiv:2403.05334
Published Date
2024/3/8
Systems and methods for reconstructing a scene in three dimensions from a two-dimensional image
Systems and methods described herein relate to reconstructing a scene in three dimensions from a two-dimensional image. One embodiment processes an image using a detection transformer to detect an object in the scene and to generate a NOCS map of the object and a background depth map; uses MLPs to relate the object to a differentiable database of object priors (PriorDB); recovers, from the NOCS map, a partial 3D object shape; estimates an initial object pose; fits a PriorDB object prior to align in geometry and appearance with the partial 3D shape to produce a complete shape and refines the initial pose estimate; generates an editable and re-renderable 3D scene reconstruction based, at least in part, on the complete shape, the refined pose estimate, and the depth map; and controls the operation of a robot based, at least in part, on the editable and re-renderable 3D scene reconstruction.
Published Date
2024/1/30
Neural amortized inference for nested multi-agent reasoning
Multi-agent interactions, such as communication, teaching, and bluffing, often rely on higher-order social inference, i.e., understanding how others infer oneself. Such intricate reasoning can be effectively modeled through nested multi-agent reasoning. Nonetheless, the computational complexity escalates exponentially with each level of reasoning, posing a significant challenge. However, humans effortlessly perform complex social inferences as part of their daily lives. To bridge the gap between human-like inference capabilities and computational limitations, we propose a novel approach: leveraging neural networks to amortize high-order social inference, thereby expediting nested multi-agent reasoning. We evaluate our method in two challenging multi-agent interaction domains. The experimental results demonstrate that our method is computationally efficient while exhibiting minimal degradation in accuracy.
Authors
Kunal Jha,Tuan Anh Le,Chuanyang Jin,Yen-Ling Kuo,Joshua B Tenenbaum,Tianmin Shu
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Published Date
2024/3/25
Inferring the future by imagining the past
A single panel of a comic book can say a lot: it can depict not only where the characters currently are, but also their motions, their motivations, their emotions, and what they might do next. More generally, humans routinely infer complex sequences of past and future events from a static snapshot of a dynamic scene, even in situations they have never seen before. In this paper, we model how humans make such rapid and flexible inferences. Building on a long line of work in cognitive science, we offer a Monte Carlo algorithm whose inferences correlate well with human intuitions in a wide variety of domains, while only using a small, cognitively-plausible number of samples. Our key technical insight is a surprising connection between our inference problem and Monte Carlo path tracing, which allows us to apply decades of ideas from the computer graphics community to this seemingly-unrelated theory of mind task.
Authors
Kartik Chandra,Tony Chen,Tzu-Mao Li,Jonathan Ragan-Kelley,Josh Tenenbaum
Journal
Advances in Neural Information Processing Systems
Published Date
2024/2/13
DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models
Nature evolves creatures with a high complexity of morphological and behavioral intelligence, meanwhile computational methods lag in approaching that diversity and efficacy. Co-optimization of artificial creatures' morphology and control in silico shows promise for applications in physical soft robotics and virtual character creation; such approaches, however, require developing new learning algorithms that can reason about function atop pure structure. In this paper, we present DiffuseBot, a physics-augmented diffusion model that generates soft robot morphologies capable of excelling in a wide spectrum of tasks.\name bridges the gap between virtually generated content and physical utility by (i) augmenting the diffusion process with a physical dynamical simulation which provides a certificate of performance, and (ii) introducing a co-design procedure that jointly optimizes physical design and control by leveraging information about physical sensitivities from differentiable simulation. We showcase a range of simulated and fabricated robots along with their capabilities. Check our website: https://diffusebot. github. io/
Authors
Tsun-Hsuan Johnson Wang,Juntian Zheng,Pingchuan Ma,Yilun Du,Byungchul Kim,Andrew Spielberg,Josh Tenenbaum,Chuang Gan,Daniela Rus
Journal
Advances in Neural Information Processing Systems
Published Date
2024/2/13
Intuitive physics as probabilistic inference
Intuitive physics as probabilistic inference - WRAP: Warwick Research Archive Portal Skip to content Skip to navigation University of Warwick Study | Research | Business | Alumni | News | About University of Warwick Publications service & WRAP Highlight your research WRAP Home Search WRAP Browse by Warwick Author Browse WRAP by Year Browse WRAP by Subject Browse WRAP by Department Browse WRAP by Funder Browse Theses by Department Publications Service Home Search Publications Service Browse by Warwick Author Browse Publications service by Year Browse Publications service by Subject Browse Publications service by Department Browse Publications service by Funder Help & Advice University of Warwick The Library Login Admin Intuitive physics as probabilistic inference Tools + Tools Smith, KA, Hamrick, JB, Sanborn, Adam N., Battaglia, PW, Gerstenberg, T., Ullman, TD and …
Authors
KA Smith,JB Hamrick,Adam N Sanborn,PW Battaglia,T Gerstenberg,TD Ullman,JB Tenenbaum
Published Date
2024
Professor FAQs
What is Joshua B. Tenenbaum's h-index at Massachusetts Institute of Technology?
The h-index of Joshua B. Tenenbaum has been 115 since 2020 and 137 in total.
What are Joshua B. Tenenbaum's top articles?
The articles with the titles of
What Planning Problems Can A Relational Neural Network Solve?
Bayesian models of cognition: reverse engineering the mind
WatChat: Explaining perplexing programs by debugging mental models
Systems and methods for reconstructing a scene in three dimensions from a two-dimensional image
Neural amortized inference for nested multi-agent reasoning
Inferring the future by imagining the past
DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models
Intuitive physics as probabilistic inference
...
are the top articles of Joshua B. Tenenbaum at Massachusetts Institute of Technology.
What are Joshua B. Tenenbaum's research interests?
The research interests of Joshua B. Tenenbaum are: Cognitive science, artificial intelligence, machine learning, computational neuroscience, cognitive psychology
What is Joshua B. Tenenbaum's total number of citations?
Joshua B. Tenenbaum has 102,796 citations in total.
What are the co-authors of Joshua B. Tenenbaum?
The co-authors of Joshua B. Tenenbaum are William T. Freeman, Antonio Torralba, Ruslan Salakhutdinov, Thomas L. Griffiths, Noah D. Goodman, Samuel Gershman.