Yash Bhalgat
DPhil (PhD) Researcher, Visual Geometry Group at University of Oxford
Oxford, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolYash Bhalgat is a DPhil researcher at Oxford's Visual Geometry Group with 11 years of experience building and deploying cutting-edge computer vision and multimodal AI systems, specializing in video generation, 3D/4D reconstruction and vision-language foundation models. He combines deep academic pedigree (IIT Bombay, UMich, Oxford) and industry impact from Qualcomm AI Research to startups, where he translated research into low-power AR vision systems, cloud video pipelines, and production tracking tools. His work spans from efficient model design and quantization for hardware-constrained settings to large-scale generative 3D foundation models, with publications in CVPR, NeurIPS, ECCV and more. An active practitioner in neural graphics, he implemented a PyTorch HashNeRF renderer and contributed core embedding and interpolation components, reflecting hands-on ML engineering alongside theory. Mentorship, multiple patents, and internships at Meta Reality Labs and IBM underscore his ability to move ideas from prototype to product.
10 years of coding experience
1 year of employment as a software developer
Masters, Computer Science, Masters, Computer Science at University of Michigan - Rackham Graduate SchoolDoctor of Philosophy - PhD, Artificial Intelligence and Computer Vision, Doctor of Philosophy - PhD, Artificial Intelligence and Computer Vision at University of OxfordIndian Institute of Technology Bombay
Stackoverflow
1reputation
571reached
0answers
1question
Github Skills (9)
neural-network10
pytorch10
machine-learning10
computer-graphics10
3d-reconstruction10
computer-vision9
serf8
react-hooks6
react6
Programming languages (6)
Github contributions (5)
yashbhalgat/HashNeRF-pytorch
Jan 2022 - Jan 2023
Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/
Role in this project:
ML Engineer
ML EngineerContributions:36 commits, 1 PR, 10 pushes in 11 months
Contributions summary:Yash implemented a batchwise HashRenderer using PyTorch, which included significant code changes in `run_nerf_helpers.py`, `run_nerf.py`, and `utils.py`. They worked on core components for the HashNeRF model, specifically focusing on the `HashEmbedder` and related trilinear interpolation, and integrating it into the NeRF framework. The contributions also involved adjusting parameters for the training process and ensuring the integration of their implementation into the overall system.
hashingsigned-distance-functionstrainingprimitivesnvidia
yashbhalgat/yashbhalgat.github.io
Jul 2020 - Mar 2025
Contributions:145 pushes, 1 branch in 4 years 8 months
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.