CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 10 Dec 2025 00:59:00 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6938c5d4-5ba3" expires: Mon, 29 Dec 2025 15:18:21 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 9160:123DE:8F9AEA:A123BE:69529962 accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 15:08:21 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210076-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767020901.159108,VS0,VE205 vary: Accept-Encoding x-fastly-request-id: 3193a65f806255b2d4d8dab54b4ac6852c263aa7 content-length: 4877 Joe Ortiz

I am a Senior Research Scientist at Google DeepMind working on world models. Before that, I was a postdoc at Meta AI (FAIR) working on 3D perception for robotics. My recent research focus is on generative world models that can be used for reasoning and planning across long horizons. I'm interested in ways to make world models that are real-time and consistent by leveraging efficient abstractions including 3D.

I graduated from my PhD at Imperial College London in 2023, advised by Prof. Andrew Davison. There my work focused on 1) graphical representations and distributed inference algorithms on graphs, and 2) training neural scene representations via continual learning for real-time robotics. I completed my undergraduate and Masters in Physics at the University of Oxford.

Publications

Improving Transformer World Models for Data-Efficient RL

ICML 2025

Antoine Dedieu*, Joseph Ortiz*, Xinghua Lou, Carter Wendelken, Wolfgang Lehrach, J Swaroop Guntupalli, Miguel Lazaro-Gredilla, Kevin Patrick Murphy

[Paper]

DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors

NeurIPS 2024

Joseph Ortiz, Antoine Dedieu, Wolfgang Lehrach, Swaroop Guntupalli, Carter Wendelken, Ahmad Humayun, Guangyao Zhou, Sivaramakrishnan Swaminathan, Miguel Lázaro-Gredilla, Kevin Murphy

[Paper] [Code/Data]

Diffusion Model Predictive Control

ArXiv 2024

Guangyao Zhou, Sivaramakrishnan Swaminathan, Rajkumar Vasudeva Raju, J Swaroop Guntupalli, Wolfgang Lehrach, Joseph Ortiz, Antoine Dedieu, Miguel Lázaro-Gredilla, Kevin Murphy

[Paper]

A Touch, Vision, and Language Dataset for Multimodal Alignment

ICML 2024

Letian Fu, Gaurav Datta, Huang Huang, William Chung-Ho Panitch, Jaimyn Drake, Joseph Ortiz, Mustafa Mukadam, Mike Lambeta, Roberto Calandra, Ken Goldberg

[Project Page] [Paper] [Code] [Dataset] [Models]

Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation

Science Robotics 2024

Sudharshan Suresh, Haozhi Qi, Tingfan Wu, Taosha Fan, Luis Pineda, Mike Lambeta, Jitendra Malik, Mrinal Kalakrishnan, Roberto Calandra, Michael Kaess, Joseph Ortiz, Mustafa Mukadam

[Project Page] [Paper] [ArXiv] [Video]

Perceiving Extrinsic Contacts from Touch Improves Learning Insertion Policies

ArXiv 2023

Carolina Higuera, Joseph Ortiz, Haozhi Qi, Luis Pineda, Byron Boots, Mustafa Mukadam

[Paper] [Video] [Code]

Decentralization and Acceleration Enables Large-Scale Bundle Adjustment

RSS 2023

Taosha Fan, Joseph Ortiz, Ming Hsiao, Maurizio Monge, Jing Dong, Todd Murphey, Mustafa Mukadam

[Project Page] [Paper] [Video] [Code]

Gaussian Belief Propagation for Real-Time Decentralised Inference

PhD Thesis

Joseph Ortiz

[pdf]

Theseus: A Library for Differentiable Nonlinear Optimization

NeurIPS 2022

Luis Pineda, Taosha Fan, Maurizio Monge, Shobha Venkataraman, Paloma Sodhi,
Ricky Chen, Joseph Ortiz, Daniel DeTone, Austin Wang, Stuart Anderson,
Jing Dong, Brandon Amos, Mustafa Mukadam

[Project Page] [Paper] [Code]