Former Ph.D. Student · Ph.D. NYU 2023
Now: Extend AI (vision-language models and multimodal agentic systems)
- Ph.D., New York University (Tandon School of Engineering), 2023
- B.E. (Hons.), Electrical and Electronics Engineering, Birla Institute of Technology and Science, Pilani (Goa), 2014
Ameya was a Ph.D. student in the Department of Electrical and Computer Engineering at Iowa State University, jointly supervised by Prof. Soumik Sarkar and Prof. Chinmay Hegde. He received his undergraduate degree in Electrical and Electronics Engineering from Birla Institute of Technology and Science, Pilani, in 2014, and previously worked at SigTuple Technologies in Bengaluru on learning-based systems for medical images. His research interests included robust machine learning with applications in medicine and manufacturing, distributed learning, and cyber-physical systems.
He moved to New York University in January 2020 to continue his Ph.D. with Prof. Hegde and completed it in 2023. He now builds vision-language models and multimodal agentic systems at Extend AI.
Research interests: Robust deep learning, generative models with structured constraints, vision-language models, multimodal agentic systems
Publications with the lab (17)
- Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing — 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) (2024)
- Zero‐shot insect detection via weak language supervision — The Plant Phenome Journal (2024)
- NeuFENet: neural finite element solutions with theoretical bounds for parametric PDEs — Engineering with Computers (2024)
Show all 17
- Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos — IEEE Transactions on Intelligent Transportation Systems (2024)
- Generative semantic domain adaptation for perception in autonomous driving — Journal of big data analytics in transportation (2022)
- Differentiable spline approximations — Advances in neural information processing systems (2021)
- Fast inverse design of microstructures via generative invariance networks — Nature Computational Science (2021)
- DiffNet: Neural Field Solutions of Parametric Partial Differential Equations — arXiv preprint arXiv:2110.01601 (2021)
- Deep generative models that solve pdes: Distributed computing for training large data-free models — 2020 IEEE/ACM Workshop on Machine Learning in High Performance Computing … (2020)
- InvNet: encoding geometric and statistical invariances in deep generative models — Proceedings of the AAAI Conference on Artificial Intelligence (2020)
- Differentiable programming for piecewise polynomial functions — (2020)
- Encoding Invariances in Deep Generative Models — arXiv preprint arXiv:1906.01626 (2019)
- Semantic domain adaptation for deep classifiers via gan-based data augmentation — Proc. Conf. Neural Inf. Process. Syst. Workshops (2019)
- Generative models for solving nonlinear partial differential equations — Proc. of NeurIPS Workshop on ML for Physics (2019)
- Attribute-controlled traffic data augmentation using conditional generative models — CVPR Workshop on Vision for All Seasons (VAS) (2019)
- Semantic adversarial attacks: Parametric transformations that fool deep classifiers — Proceedings of the IEEE/CVF international conference on computer vision … (2019)
- Binary 2d morphologies of polymer phase separation: Dataset and python toolbox — (2019)
ameya (@) iastate.eduPersonal WebsiteGoogle ScholarGitHub