Alert button
Picture for Michael J. Tarr

Michael J. Tarr

Alert button

Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

Oct 23, 2023
Gabriel Sarch, Yue Wu, Michael J. Tarr, Katerina Fragkiadaki

Viaarxiv icon

BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity

Oct 06, 2023
Andrew F. Luo, Margaret M. Henderson, Michael J. Tarr, Leila Wehbe

Viaarxiv icon

Thinking Like an Annotator: Generation of Dataset Labeling Instructions

Jun 24, 2023
Nadine Chang, Francesco Ferroni, Michael J. Tarr, Martial Hebert, Deva Ramanan

Viaarxiv icon

Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models

Jun 05, 2023
Andrew F. Luo, Margaret M. Henderson, Leila Wehbe, Michael J. Tarr

Figure 1 for Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models
Figure 2 for Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models
Figure 3 for Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models
Figure 4 for Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models
Viaarxiv icon

Quantifying the Roles of Visual, Linguistic, and Visual-Linguistic Complexity in Verb Acquisition

Apr 05, 2023
Yuchen Zhou, Michael J. Tarr, Daniel Yurovsky

Figure 1 for Quantifying the Roles of Visual, Linguistic, and Visual-Linguistic Complexity in Verb Acquisition
Figure 2 for Quantifying the Roles of Visual, Linguistic, and Visual-Linguistic Complexity in Verb Acquisition
Figure 3 for Quantifying the Roles of Visual, Linguistic, and Visual-Linguistic Complexity in Verb Acquisition
Figure 4 for Quantifying the Roles of Visual, Linguistic, and Visual-Linguistic Complexity in Verb Acquisition
Viaarxiv icon

TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors

Jul 21, 2022
Gabriel Sarch, Zhaoyuan Fang, Adam W. Harley, Paul Schydlo, Michael J. Tarr, Saurabh Gupta, Katerina Fragkiadaki

Figure 1 for TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
Figure 2 for TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
Figure 3 for TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
Figure 4 for TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
Viaarxiv icon

Learning Neural Acoustic Fields

Apr 04, 2022
Andrew Luo, Yilun Du, Michael J. Tarr, Joshua B. Tenenbaum, Antonio Torralba, Chuang Gan

Figure 1 for Learning Neural Acoustic Fields
Figure 2 for Learning Neural Acoustic Fields
Figure 3 for Learning Neural Acoustic Fields
Figure 4 for Learning Neural Acoustic Fields
Viaarxiv icon

Alpha Net: Adaptation with Composition in Classifier Space

Aug 17, 2020
Nadine Chang, Jayanth Koushik, Michael J. Tarr, Martial Hebert, Yu-Xiong Wang

Figure 1 for Alpha Net: Adaptation with Composition in Classifier Space
Figure 2 for Alpha Net: Adaptation with Composition in Classifier Space
Figure 3 for Alpha Net: Adaptation with Composition in Classifier Space
Figure 4 for Alpha Net: Adaptation with Composition in Classifier Space
Viaarxiv icon

Learning Intermediate Features of Object Affordances with a Convolutional Neural Network

Feb 20, 2020
Aria Yuan Wang, Michael J. Tarr

Figure 1 for Learning Intermediate Features of Object Affordances with a Convolutional Neural Network
Figure 2 for Learning Intermediate Features of Object Affordances with a Convolutional Neural Network
Figure 3 for Learning Intermediate Features of Object Affordances with a Convolutional Neural Network
Figure 4 for Learning Intermediate Features of Object Affordances with a Convolutional Neural Network
Viaarxiv icon

BOLD5000: A public fMRI dataset of 5000 images

Sep 05, 2018
Nadine Chang, John A. Pyles, Abhinav Gupta, Michael J. Tarr, Elissa M. Aminoff

Figure 1 for BOLD5000: A public fMRI dataset of 5000 images
Figure 2 for BOLD5000: A public fMRI dataset of 5000 images
Figure 3 for BOLD5000: A public fMRI dataset of 5000 images
Figure 4 for BOLD5000: A public fMRI dataset of 5000 images
Viaarxiv icon