Amogh Joshi

I am an undergraduate student at Princeton University, studying electrical and computer engineering. I'm broadly interested in computer vision & graphics, robotics, and cognitive science.

I am a researcher in Princeton's Computational Imaging Lab, where I've worked on various aspects of the imaging pipeline, including neural rendering, scene reconstruction, and optical sensing - for applications ranging from autonomous driving to endoscopic imaging. I'm also a member of the Neuroscience of Cognitive Control Lab, where I develop computational cognitive science approaches to understanding large visual & language models.

I work as an autonomous driving engineer at Monarch Tractor, where I've developed deep learning-based pipelines for autonomous navigation, perception algorithms for operator safety, and more.

std::cout << "amoghjoshi" << "@" << "princeton.edu" << std::endl;

GitHub  /  Google Scholar  /  LinkedIn

profile photo

News

  • [Oct 2024]: I was invited to give a lecture on AgML and agricultural machine learning at New Mexico State University.
  • [Jul 2024]: Neural Light Spheres was accepted to SIGGRAPH Asia 2024.

Research

I'm currently researching neural rendering and scene reconstruction in the Computational Imaging Lab at Princeton, and computational cognitive science in the Neuroscience of Cognitive Control Lab.

Additionally, I'm an affiliate of the AI Institute for Next-Generation Food Systems, where I've led the development of AgML. Previously, I've worked on synthetic crop modeling with Project GEMINI, generative modeling for agriculture at the Plant AI & Biophysics Lab at UC Davis, and analysis of image sharing behavior at the Information Ecosystems Lab at UMD.

project image

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem


Declan Campbell, Sunayana Rane, Tyler Giallanza, Nicolò De Sabbata, Kia Ghods, Amogh Joshi, Alexander Ku, Steven M. Frankland, Thomas L. Griffiths, Jonathan D. Cohen, Taylor W. Webb
NeurIPS, 2024
publication / arXiv

We identify that state-of-the-art VLMs fail at basic multi-object reasoning due to the binding problem, which limits simultaneous entity representation, similar to human brain processing.
project image

Neural Light Spheres for Implicit Image Stitching and View Synthesis


Ilya Chugunov, Amogh Joshi, Kiran Murthy, Francois Bleibel, Felix Heide
SIGGRAPH Asia, 2024
project page / publication / arXiv

We design a spherical neural light field model for implicit panoramic image stitching and re-rendering, capable of handling depth parallax, view-dependent lighting, and scene motion.
project image

Examining Similar and Ideologically Correlated Imagery in Online Political Communication


Amogh Joshi, Cody Buntain
ICWSM, 2024
publication / arXiv

We investigate how US national politicians' use of various visual media on Twitter reflects their political positions, identifying limitations in standard image characterization methods.
project image

An Open Source Simulation Toolbox for Annotation of Images and Point Clouds in Agricultural Scenarios


Dario Guevara, Amogh Joshi, Pranav Raja, Elisabeth Forrestel, Brian Bailey, Mason Earles
ISVC, 2023
publication

We present an open-source simulation toolbox designed for the easy generation of synthetic labeled data for both RGB imagery and point cloud information, applicable to a wide array of cultivars.
project image

Standardizing and Centralizing Datasets for Efficient Training of Agricultural Deep Learning Models


Amogh Joshi, Dario Guevara, Mason Earles
Plant Phenomics, 2023
publication / arXiv

We present methods for enhancing data efficiency in agricultural computer vision, which improves performance and reduces training time, and introduce a novel set of model benchmarks.
project image

Exploiting the Right: Inferring Ideological Alignment in Online Influence Campaigns Using Shared Images


Amogh Joshi, Cody Buntain
ICWSM, 2022
publication / arXiv / press

We develop models to analyze the ideological presentation of foreign Twitter accounts based on shared images, revealing inconsistencies in ideological positions across different content types.

Major Projects

The following are major projects which I have either led or significantly contributed to.

project image

AgML: An Open-Source Library for Agricultural Machine Learning


AI Institute for Next Generation Food Systems

project / info / press

Since its inception, I have led the development of AgML. We have aggregated the world's largest collection of agricultural deep learning datasets, produced benchmarks and pretrained weights for state-of-the-art models, and developed a suite of tools for data preprocessing, model training, and deployment in an easy-to-use API.

Other

When I'm not working on the development of imaging systems, I enjoy using them to capture photographs of our world: check out my photography page for some highlights from my travels. I'm also an avid reader (of all genres, though I'm on a particular sci-fi kick right now): to check out my reading list, visit my Goodreads page.


Design and source code adapted from Jon Barron's website.