Education
- Ph.D., Mechanical Engineering (AI & Deep Learning) – Georgia Institute of Technology, USA (2019–2023)
Thesis: Learning 3D Robotics Perception using Inductive Priors - M.S., Mechanical Engineering (Robotics) – Georgia Institute of Technology, USA (2019–2023)
- B.S., Mechanical Engineering – GIK Institute of Engineering Sciences and Technology, Pakistan (2011–2015)
Graduated Magna Cum Laude; Dean’s Honor Roll (all semesters)
Research & Professional Experience
- Research Scientist– Toyota Research Institute (2024–Present)
- Lead projects on 3D perception, large behavior models, and multimodal AI for robotics.
- Managed collaborations with UC Berkeley, CMU, and other institutions.
- Published in CVPR, ECCV, ICRA, IROS; filed 8+ patents.
- Research Intern – Toyota Research Institute (2021–2022)
- Developed single-shot reconstruction and pose estimation methods.
- Co-authored papers in ICRA and ECCV; filed multiple U.S. patents.
- Research Intern – SRI International (2020)
- Designed a novel vision-language navigation model (1 publication, 1 patent).
- Graduate Research Assistant – Georgia Tech (2019–2023)
- Led projects in multimodal AI, robot perception, shape reconstruction, and 6D pose estimation.
- Funded by Toyota Research Institute and DARPA’s Lifelong Learning Machines program.
Biography
Dr. Zubair Irshad is an accomplished AI and Robotics researcher with a Ph.D. in Mechanical Engineering from the Georgia Institute of Technology, specializing in Artificial Intelligence and Deep Learning. His work spans academia and industry, with expertise in 3D perception, robot learning, foundation models, and multimodal AI.
Dr. Irshad has published 25+ peer-reviewed papers at leading conferences such as CVPR, ICCV, ECCV, ICRA, and IROS, earning 1,600+ citations (h-index: 12). He holds 12+ patents and has served as a reviewer for 40+ papers across premier venues including CVPR, NeurIPS, ICLR, ECCV, and RSS. Beyond research, he has mentored over 10 researchers and taught multiple courses in deep learning, robotics, and computer vision.
Currently, at Toyota Research Institute, Dr. Irshad leads projects in 3D vision and robotics, including work on large behavior models and collaborations with UC Berkeley, CMU, and other academic partners. He has played a central role in advancing multi-task policy learning for robotics foundation models.
Selected Publications
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion, CVPR 2025.
- ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping, CVPR 2025.
- EmbodiedSplat: Personalized Navigation with Gaussian Splats, ICCV 2025.
- NeRF-MAE: Self-Supervised 3D Representation Learning for Neural Radiance Fields, ECCV 2024.
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset, RSS 2024.
- (25+ total publications in CVPR, ICCV, ECCV, ICRA, IROS)
Patents (Selected)
- Multi-view geometric diffusion for 3D scene reconstruction (US Patent Application).
- Systems for reconstructing articulated objects using 3D Gaussian Splatting (US Patent Application).
- Neural Radiance Field–based computer vision representation for robotics (US Patent Application).
- (12+ patents filed in AI and robotics)
Teaching & Mentorship
- Graduate Teaching Assistant – Deep Learning (Georgia Tech, 2021).
- Teaching Practicum – Robotics (Georgia Tech, 2021).
- Mentored 10+ students and interns (many now at Google, Waymo, C3.AI, and PhD programs worldwide).
Talks & Workshops
- Embodied AI for 3D Perception leveraging Inductive Priors – GIKI (2025).
- Towards Embodied 3D Foundation Models – Habib University, Pakistan (2024).
- Neural Fields in Robotics and Beyond – Stanford & Facebook AI Research (2023–2024).
- Co-organizer: Robo3D-VLMs Workshop (CVPR 2025), RoboNeRF Workshop (ICRA 2024).
