Ph.D. 2020, Postdoc 2020–2021
Now: Data Scientist, Translational AI Center (TrAC), Iowa State University
- Ph.D., Mechanical Engineering, Iowa State University, 2020
- B.E. (Hons.), Mechanical Engineering, Birla Institute of Technology and Science, Pilani, 2014
Aditya completed his Ph.D. at Iowa State University in 2020 under the joint supervision of Dr. Adarsh Krishnamurthy and Dr. Soumik Sarkar, then stayed on as a Postdoctoral Research Associate from May 2020 to December 2021. He received his undergraduate degree from Birla Institute of Technology and Science, Pilani, in 2014, and worked at FMC Technologies (now TechnipFMC) for two years before graduate school. His research interests included design for manufacturing, machine learning, and high-performance computing applied to engineering problems.
He is now a Data Scientist at the Translational AI Center (TrAC) at Iowa State University, working on physics-informed machine learning, GPU computing, neural PDE solvers, decentralized learning, and scientific machine learning.
Research interests: Physics-informed machine learning, scientific machine learning, neural PDE solvers, GPU computing, decentralized learning, design for manufacturing
Publications with the lab (79)
- In-context adaptation of VLMs for few-shot cell detection in optical microscopy — Frontiers in Artificial Intelligence (2026)
- DeCAF: Decentralized consensus-and-factorization for low-rank adaptation of foundation models — Neural Networks (2026)
- ADKO: Agentic Decentralized Knowledge Optimization — arXiv (2026)
Show all 79
- TabQL: In-Context Q-Learning with Tabular Foundation Models — arXiv (2026)
- BPS2026 – In-context adaptation of vision language models (VLMs) for few-shot cell detection in microscopy — Biophysical Journal (2026)
- COOPO: Cyclic Offline-Online Policy Optimization Algorithm — arXiv (2026)
- Lighting-aware Unified Model for Instance Segmentation — arXiv (2026)
- Bidirectional linear recurrent models for sequence-level multisource fusion — Information Fusion (2026)
- WeedNet: a foundation model-based global-to-local AI approach for weed species identification and classification — Nature Communications (2026)
- Procedural generation of 3D maize plant architecture from LiDAR data — Computers and Electronics in Agriculture (2025)
- Decentralized relaxed smooth optimization with gradient descent methods — arXiv preprint arXiv:2508.08413 (2025)
- Towards large reasoning models for agriculture — arXiv preprint arXiv:2505.19259 (2025)
- SC-NeRF: NeRF-based Point Cloud Reconstruction using a Stationary Camera for Agricultural Applications — Proceedings of the Computer Vision and Pattern Recognition Conference (2025)
- Conversational LLM-based decision support for defect classification in AFM images — IEEE Open Journal of Instrumentation and Measurement, IEEE (2025)
- Leveraging vision language models for specialized agricultural tasks — 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV … (2025)
- Robust soybean seed yield estimation using high-throughput ground robot videos — Frontiers in Plant Science (2025)
- Benchmarking scientific machine-learning approaches for flow prediction around complex geometries — Communications Engineering (2025)
- 3D multiphase heterogeneous microstructure generation using conditional latent diffusion models — Digital Discovery (2025)
- FUSE: First-Order and Second-Order Unified Synthesis in Stochastic Optimization — 2025 IEEE Conference on Artificial Intelligence (CAI) (2025)
- Foundation Model Efficient Fine-Tuning in Centralized and Federated Settings — 2025 IEEE International Conference on Big Data (BigData) (2025)
- Assisted few-shot learning for vision-language models in agricultural stress phenotype identification — Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning (2024)
- A unified convergence theory for large language model efficient fine-tuning — OPT 2024: Optimization for Machine Learning (2024)
- Class‐specific data augmentation for plant stress classification — The Plant Phenome Journal (2024)
- STITCH: Surface reconstrucTion using Implicit neural representations with Topology Constraints and persistent Homology — arXiv preprint arXiv:2412.18696 (2024)
- AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning — Computers and Electronics in Agriculture (2026)
- Geometry matters: benchmarking scientific ml approaches for flow prediction around complex geometries — arXiv preprint arXiv:2501.01453 (2024)
- Flowbench: A large scale benchmark for flow simulation over complex geometries — arXiv preprint arXiv:2409.18032 (2024)
- Dominating Set Model Aggregation for communication-efficient decentralized deep learning — Neural Networks (2024)
- Neural pde solvers for irregular domains — Computer-Aided Design (2024)
- Out-of-distribution detection algorithms for robust insect classification — Plant Phenomics (2024)
- Latent diffusion models for structural component design — Computer-Aided Design (2024)
- Zero‐shot insect detection via weak language supervision — The Plant Phenome Journal (2024)
- SDFConnect: Neural implicit surface reconstruction of a sparse point cloud with topological constraints — Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern … (2024)
- Dimat: Decentralized iterative merging-and-training for deep learning models — Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern … (2024)
- NeuFENet: neural finite element solutions with theoretical bounds for parametric PDEs — Engineering with Computers (2024)
- Evaluating neural radiance fields for 3D plant geometry reconstruction in field conditions — Plant Phenomics (2024)
- Evaluating NeRFs for 3D Plant Geometry Reconstruction in Field Conditions — Iowa State University Digital Repository (Iowa State University) (2024)
- 3D reconstruction of plants using probabilistic voxel carving — Computers and Electronics in Agriculture (2023)
- Deep learning-based 3D multigrid topology optimization of manufacturable designs — Engineering Applications of Artificial Intelligence (2023)
- SpecXAI--Spectral interpretability of deep learning models — arXiv preprint arXiv:2302.09949 (2023)
- Out-of-distribution algorithms for robust insect classification — 2nd AAAI Workshop on AI for Agriculture and Food Systems (2023)
- Deep implicit surface reconstruction of 3d plant geometry from point cloud — AI for Agriculture and Food Systems (2022)
- Physics-aware machine learning surrogates for real-time manufacturing digital twin — Manufacturing Letters (2022)
- Nurbs-diff: A differentiable programming module for nurbs — Computer-Aided Design (2022)
- Generative design of material microstructures for organic solar cells using diffusion models — AI for Accelerated Materials Design NeurIPS 2022 Workshop (2022)
- Concept activation vectors for generating user-defined 3d shapes — Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern … (2022)
- Distributed online non-convex optimization with composite regret — 2022 58th Annual Allerton Conference on Communication, Control, and … (2022)
- MDPGT: momentum-based decentralized policy gradient tracking — Proceedings of the AAAI conference on artificial intelligence (2022)
- Multi-resolution 3D CNN for learning multi-scale spatial features in CAD models — Computer Aided Geometric Design (2021)
- Differentiable spline approximations — Advances in neural information processing systems (2021)
- Neural-network model for force prediction in multi-principal-element alloys — Computational Materials Science (2021)
- On consensus-optimality trade-offs in collaborative deep learning — Frontiers in artificial intelligence (2021)
- A fast saddle-point dynamical system approach to robust deep learning — Neural Networks (2021)
- Fast inverse design of microstructures via generative invariance networks — Nature Computational Science (2021)
- Algorithmically-consistent deep learning frameworks for structural topology optimization — Engineering Applications of Artificial Intelligence (2021)
- DiffNet: Neural Field Solutions of Parametric Partial Differential Equations — arXiv preprint arXiv:2110.01601 (2021)
- Decentralized Deep Learning Using Momentum-Accelerated Consensus — Preprint (2021)
- Nurbs-diff: A differentiable nurbs layer for machine learning CAD applications — arXiv preprint arXiv:2104.14547 (2021)
- Multigrid Distributed Deep CNNs for Structural Topology Optimization — AAAI 2022 Workshop on AI for Design and Manufacturing (ADAM) (2021)
- Inverse design of microstructures via generative networks for organic solar cells — AAAI 2022 Workshop on AI for Design and Manufacturing (ADAM) (2021)
- Distributed multigrid neural solvers on megavoxel domains — Proceedings of the International Conference for High Performance Computing … (2021)
- Cross-gradient aggregation for decentralized learning from non-iid data — International conference on machine learning (2021)
- A Machine Learning Framework for Decision Support in Design and Manufacturing — ASME eBooks (2021)
- Orthogonal distance fields representation for machine-learning based manufacturability analysis — International Design Engineering Technical Conferences and Computers and … (2020)
- Differentiable programming for piecewise polynomial functions — (2020)
- Multi-Level 3D CNN for Learning Multi-Scale Spatial Features — CVPR 2019 Workshop on Deep Learning for Geometric Shape Understanding (2019)
- On higher-order moments in adam — Beyond First Order Methods in Machine Learning Workshop, NeurIPS 2019 (2019)
- A deep learning framework for design and analysis of surgical bioprosthetic heart valves — Scientific reports (2019)
- A case study of deep reinforcement learning for engineering design: Application to microfluidic devices for flow sculpting — Journal of Mechanical Design (2019)
- Flow Shape Design for Microfluidic Devices Using Deep Reinforcement Learning — Deep Reinforcement Learning Workshop, NeurIPS 2018 (2018)
- 3D Deep Learning with voxelized atomic configurations for modeling atomistic potentials in complex solid-solution alloys — Machine Learning for Molecules and Materials Workshop, NeurIPS 2018 (2018)
- Multi-resolution 3D convolutional neural networks for object recognition — arXiv preprint arXiv:1805.12254 (2018)
- Learning localized features in 3D CAD models for manufacturability analysis of drilled holes — Computer Aided Geometric Design (2018)
- A Machine-Learning Framework for Design for Manufacturability — arXiv preprint arXiv:1703.01499 (2017)
- Learning and visualizing localized geometric features using 3d-cnn: An application to manufacturability analysis of drilled holes — NIPS 2017 Symposium on Interpretable Machine Learning (2017)
- A forward-backward approach for visualizing information flow in deep networks — NIPS 2017 Symposium on Interpretable Machine Learning (2017)
- Collaborative deep learning in fixed topology networks — Advances in Neural Information Processing Systems (2017)
- Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes — arXiv preprint arXiv:1612.02141 (2016)
- A Deep 3D Convolutional Neural Network Based Design for Manufacturability Framework — arXiv preprint arXiv:1612.02141 (2016)