Avinash Paliwal
Founding Research Scientist at Nuance Labs
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolAvinash Paliwal is a Founding Research Scientist with seven years of experience building production-grade 3D computer vision and generative video systems, currently working at Nuance Labs after founding research efforts at Morphic. He specializes in diffusion-based video generation, 3D Gaussian Splatting, and self-supervised video-to-video camera control, and has shipped features like image-to-video 3D motion and large-model fine-tuning pipelines for production. Avinash combines deep academic rigor—a Ph.D. from Texas A&M and publications at CVPR, ICCV, ECCV and SIGGRAPH Asia—with hands-on engineering, shown by open-source contributions such as a PyTorch Super-SloMo implementation. He has a strong track record of scaling training and data pipelines across multi-node distributed setups and exploring agentic text-to-trajectory planning with LLMs for scene-aware camera paths. Based in Seattle, he bridges academic research and product delivery, often leaning on practical optimizations born from embedded-systems experience earlier in his career.
7 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Engineering, Doctor of Philosophy - PhD, Computer Engineering at Texas A&M UniversityBachelor of Technology (B.Tech.), Electronics and Communications Engineering, Bachelor of Technology (B.Tech.), Electronics and Communications Engineering at Visvesvaraya National Institute of Technology
Github Skills (5)
pytorch10
convolutional-neural-networks10
deep-learning10
python10
deep-neural-networks9
Programming languages (2)
Github contributions (5)
avinashpaliwal/Super-SloMo
Dec 2018 - Nov 2020
PyTorch implementation of Super SloMo by Jiang et al.
Role in this project:
ML Engineer
ML EngineerContributions:39 commits, 7 PRs, 34 pushes in 1 year 11 months
Contributions summary:Avinash primarily contributed to the PyTorch implementation of the Super SloMo video interpolation model. Their work involved modifying the training script, fixing bugs, adding comments, and updating the dataset creation process. They also developed a video conversion script to apply the Super SloMo model to input videos. These contributions demonstrate an active role in enhancing the model's functionality and usability.
pytorchvideo-frame-interpolationsuper-slomopytorch-implmentionslow-motion
avinashpaliwal/MaskDnGAN
Mar 2021 - Apr 2022
Official PyTorch implementation of "Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask"
Contributions:6 commits, 5 pushes, 1 branch in 1 year 1 month
denoisingmultistagepytorch
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.