Matt Wallingford

I am a research scientist on the PRIOR team at the Allen Institute for AI (AI2). I received my PhD in Computer Science from the University of Washington, where I was advised by Ali Farhadi.

Before Seattle, I received my B.S. in Mathematics and Physics and an M.S. in Computer Science from Cornell University, where I was advised by Bharath Hariharan.

Google Scholar LinkedIn Email CV
Matt Wallingford

Preprints

* equal contribution† core contributor

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

Abhay Deshpande*, Maya Guru*, Rose Hendrix*, Snehal Jauhri*, Ainaz Eftekhar†, Rohun Tripathi†, Max Argus†, Jordi Salvador†, Haoquan Fang†, Matthew Wallingford†, Wilbert Pumacay†, Yejin Kim†, Quinn Pfeifer, Ying-Chun Lee, Piper Wolters, Omar Rayyan, Mingtong Zhang, Jiafei Duan, Karen Farley, Winson Han, Eli Vanderbilt, Dieter Fox, Ali Farhadi, Georgia Chalvatzaki, Dhruv Shah†, Ranjay Krishna†

arXiv, 2025

paper webpage

Publications

Beyond the Frame: Generating 360° Panoramic Videos from Perspective Videos

Rundong Luo, Matt Wallingford, Ali Farhadi, Noah Snavely, Wei-Chiu Ma

International Conference on Computer Vision (ICCV), 2025

paper webpage code

From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos

Matt Wallingford, Anand Bhattad, Aditya Kusupati, Vivek Ramanujan, Matt Deitke, Aniruddha Kembhavi, Roozbeh Mottaghi, Wei-Chiu Ma, Ali Farhadi

Conference on Neural Information Processing Systems (NeurIPS), 2024

paper webpage code

Multilingual Diversity Improves Vision-Language Representations

Thao Nguyen, Matt Wallingford, Sebastin Santy, Wei-Chiu Ma, Sewoong Oh, Ludwig Schmidt, Pang Wei Koh, Ranjay Krishna

Conference on Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)

paper

Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass

Ethan Shen, Alan Fan, Sarah M. Pratt, Jae Sung Park, Matt Wallingford, Sham M. Kakade, Ari Holtzman, Ranjay Krishna, Ali Farhadi, Aditya Kusupati

Conference on Neural Information Processing Systems (NeurIPS), 2024

paper code

The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better

Scott Geng, Cheng-Yu Hsieh, Vivek Ramanujan, Matt Wallingford, Chun-Liang Li, Pang Wei Koh, Ranjay Krishna

Conference on Neural Information Processing Systems (NeurIPS), 2024

paper code

Neural Radiance Field Codebooks

Matt Wallingford, Aditya Kusupati, Alex Fang, Vivek Ramanujan, Aniruddha Kembhavi, Roozbeh Mottaghi, Ali Farhadi

International Conference on Learning Representations (ICLR), 2023

paper code

Neural Priming for Sample-Efficient Adaptation

Matt Wallingford*, Vivek Ramanujan*, Alex Fang, Aditya Kusupati, Roozbeh Mottaghi, Aniruddha Kembhavi, Ludwig Schmidt, Ali Farhadi

Conference on Neural Information Processing Systems (NeurIPS), 2023

paper code

Objaverse-XL: A Universe of 10M+ 3D Objects

Matt Deitke, Ruoshi Liu, Matt Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, Eli VanderBilt, Aniruddha Kembhavi, Carl Vondrick, Georgia Gkioxari, Kiana Ehsani, Ludwig Schmidt, Ali Farhadi

Conference on Neural Information Processing Systems (NeurIPS), 2023

paper code

FLUID: A Unified Evaluation Framework for Flexible Sequential Data

Matt Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi

Transactions on Machine Learning Research (TMLR), 2023

paper code

Task Adaptive Parameter Sharing for Multi-Task Learning

Matt Wallingford, Hao Li, Alessandro Achille, Avinash Ravichandran, Charless Fowlkes, Rahul Bhotika, Stefano Soatto

Conference on Computer Vision and Pattern Recognition (CVPR), 2022

paper code

Matryoshka Representation Learning

Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matt Wallingford, Aditya Sber, Vivek Ramanujan, Prateek Jain, Sham M. Kakade, Ali Farhadi

Conference on Neural Information Processing Systems (NeurIPS), 2022

paper code

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Aditya Kusupati, Matt Wallingford, Vivek Ramanujan, Raghav Somber, Prateek Jain, Sham Kakade, Ali Farhadi

Conference on Neural Information Processing Systems (NeurIPS), 2021

paper code

RoboTHOR: An Open Simulation-to-Real Embodied AI Platform

Matt Deitke, Winson Han, Alvaro Herrasti, Aniruddha Kembhavi, Eric Kolve, Roozbeh Mottaghi, Jordi Salvador, Dustin Schwenk, Eli VanderBilt, Matt Wallingford, Luca Weihs, Mark Yatskar, Ali Farhadi

Conference on Computer Vision and Pattern Recognition (CVPR), 2020

paper code
See all publications on Google Scholar →