Zubair Irshad
Research Scientist at Toyota Research Institute
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolZubair Irshad is a Research Scientist at Toyota Research Institute specializing in 3D computer vision, embodied AI and Large Behavioral Models, with 8+ years of deep learning experience and a PhD from Georgia Tech. His work bridges neural implicit representations (NeRFs, SDFs, Gaussian splats) and robotics applications like zero-shot grasping, 6D pose estimation, and multitask dexterous manipulation, resulting in 18+ publications, 8 US patents and 400+ citations. He has a strong track record of turning cutting-edge self-supervised and generative 3D methods into practical robotics systems, contributing core ideas to multiple CVPR/ICCV/ECCV and ICRA papers. Beyond research, he co-led multi-task policy learning for robotics foundational models, organizes community workshops (RoboNeRF ICRA’24), and maintains an influential GitHub presence with 3k+ stars. Based in Palo Alto, he balances industry research at TRI with teaching and mentorship, rapidly iterating between theory, large-scale models and real-world robot deployment.
8 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy - PhD, Mechanical Engineering, Doctor of Philosophy - PhD, Mechanical Engineering at Georgia Institute of TechnologyBachelor of Science (B.S.), Mechanical Engineering, Bachelor of Science (B.S.), Mechanical Engineering at Ghulam Ishaq Khan Institute of Engineering Sciences and Technology
English, Urdu
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (114)
pose10
radiance10
bounding10
representations10
implicit10
categorical10
deep-learning10
depth-estimation10
representation-learning10
robotics10
single-shot-detection10
autoencoder10
siggraph10
neural-rendering10
computer-vision10
Programming languages (6)
Github contributions (5)
zubair-irshad/nerf_pl
Apr 2022 - Dec 2022
NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning
Contributions:78 commits, 203 pushes, 1 branch in 7 months
pytorchlightningneural-radiance-fieldswildvolume-rendering
zubair-irshad/CenterSnap
Jan 2022 - Nov 2022
Pytorch code for ICRA'22 paper: "Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"
Contributions:36 commits, 4 PRs, 44 pushes in 9 months
3d-computer-visionauto-encodermanipulationroboticscomputer-vision
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.