Former members

Alumni

Post-doctorate Alumni

Chao Liu

Postdoctoral Researcher 2015–2017

Joined Fall 2015Now: Associate Professor, Department of Energy and Power Engineering, Tsinghua University

Ph.D., Power Engineering and Engineering Thermophysics, Tsinghua University, 2013
B.E., Thermal and Power Engineering, Huazhong University of Science and Technology, 2008

Chao joined the lab in August 2015 as a Postdoctoral Researcher in the Department of Mechanical Engineering and stayed until August 2017. His research focused on two areas. The first was diagnosis, prognosis, and health monitoring, including feature extraction and selection, fault identification, and remaining useful life prediction using physical and statistical models. The second was structural dynamics, including the dynamics of structures and rotor systems, finite element methods for the dynamics of cracked rotor systems, and experimental studies of rotor systems.

He is now an Associate Professor in the Department of Energy and Power Engineering at Tsinghua University, a rank he has held since December 2022.

Research interests: Rotating machinery dynamics, structural health monitoring, fault diagnosis and prognosis, finite element analysis, machine learning

Publications with the lab (23)

Bidirectional linear recurrent models for sequence-level multisource fusion — Information Fusion (2026)
Foundation Model Efficient Fine-Tuning in Centralized and Federated Settings — 2025 IEEE International Conference on Big Data (BigData) (2025)
The stochastic augmented lagrangian method for domain adaptation — Knowledge-Based Systems (2022)

Show all 23

Asynchronous training schemes in distributed learning with time delay — arXiv preprint arXiv:2208.13154 (2022)
Root-cause analysis for time-series anomalies via spatiotemporal graphical modeling in distributed complex systems — Knowledge-Based Systems (2021)
Data-Driven Performance Monitoring of Dynamical Systems Using Granger Causal Graphical Models — Journal of Dynamic Systems Measurement and Control (2020)
Traffic sensor health monitoring using spatiotemporal graphical modeling — International Journal of Prognostics and Health Management (2020)
Traffic System Anomaly Detection using Spatiotemporal Pattern Networks — International Journal of Prognostics and Health Management (2020)
Predicting county-scale maize yields with publicly available data — Scientific Reports (2020)
Traffic dynamics exploration and incident detection using spatiotemporal graphical modeling — Journal of Big Data Analytics in Transportation (2019)
An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems — Mechanical Systems and Signal Processing (2019)
Exploring Granger causality in dynamical systems modeling and performance monitoring — 2018 IEEE Conference on Decision and Control (CDC) (2018)
Building Energy Disaggregation using Spatiotemporal Pattern Network — (2018)
Linked read technology for assembling large complex and polyploid genomes — BMC genomics (2018)
Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network — Applied Energy (2018)
Data-driven root-cause analysis for distributed system anomalies — (2017)
Energy prediction using spatiotemporal pattern networks — Applied Energy (2017)
An unsupervised anomaly detection approach using energy-based spatiotemporal graphical modeling — Cyber-physical systems (2017)
Bridge damage detection using spatiotemporal patterns extracted from dense sensor network — Measurement Science and Technology (2017)
Data-driven persistent monitoring of Indoor Air Systems — Iowa State University Digital Repository (Iowa State University), Iowa State University (2016)
Data driven exploration of traffic network system dynamics using high resolution probe data — 2016 IEEE 55th Conference on Decision and Control (CDC) (2016)
An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed cps — 2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS … (2016)
Damage Detection of Bridge Network With Spatiotemporal Pattern Network — (2016)

cliu5 (@) iastate.eduGoogle Scholar Faculty page

Onur Rauf Bingol

Postdoctoral Researcher 2019 · now Senior Software Engineer

Joined Fall 2019

Ph.D., Mechanical Engineering, Iowa State University, 2019
M.S., Information Systems, Middle East Technical University, 2014
M.S., Metallurgical and Materials Engineering, Middle East Technical University, 2010
B.S., Metallurgical and Materials Engineering, Middle East Technical University, 2007

Onur joined the SCS Lab in Fall 2019 as a Postdoctoral Researcher. During his Ph.D., he developed a variety of open-source software libraries for computer graphics and computational mechanics, which he shared on GitHub. His research interests include computer graphics, computational geometry, high-performance computing, and robotics.

After the lab, he worked at Palo Alto Research Center (PARC). His personal website describes him as a senior software engineer focused on computational geometry, simulation, digital twins, HPC and GPU programming, and robotics.

Research interests: Computational geometry, computer graphics, simulation, digital twins, high-performance computing, robotics

Publications with the lab (1)

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)

orbingol (@) iastate.eduPersonal Website LinkedIn GitHub

Aditya Balu

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)

baditya (@) iastate.eduHomepage GitHub

Joshua Waite

Ph.D. 2024, Postdoc

Now: Data Scientist, Translational AI Center (TrAC), Iowa State University

Ph.D., Mechanical Engineering and Computer Engineering, Iowa State University, 2024
B.S., Mechanical Engineering, Iowa State University, 2019

Joshua completed his Ph.D. at Iowa State University in 2024 under the supervision of Dr. Soumik Sarkar. He then served as a Postdoctoral Research Associate with the Translational AI Center (TrAC), working on applied AI research across computer vision, multimodal AI, agentic AI systems, and simulation-based decision support.

He is now a Data Scientist at TrAC.

Research interests: Computer vision, multimodal AI, agentic AI systems, simulation-based decision support, machine learning

Publications with the lab (19)

DeCAF: Decentralized consensus-and-factorization for low-rank adaptation of foundation models — Neural Networks (2026)
A framework for AI-integrated models to assess agricultural resilience — Frontiers in Sustainable Food Systems (2026)
AI-integrated models for assessing agricultural resilience — arXiv (2026)

Show all 19

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)
Enhancing PPO With Trajectory-Aware Hybrid Policies — IEEE Transactions on Neural Networks and Learning Systems (2026)
Optimizing navigation and chemical application in precision agriculture with deep reinforcement learning and conditional action tree — Smart Agricultural Technology (2025)
RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception — Proceedings of the ACM/IEEE 16th International Conference on Cyber-Physical … (2025)
FUSE: First-Order and Second-Order Unified Synthesis in Stochastic Optimization — 2025 IEEE Conference on Artificial Intelligence (CAI) (2025)
A unified convergence theory for large language model efficient fine-tuning — OPT 2024: Optimization for Machine Learning (2024)
Diagnosis of pregnancy disorder in the first‐trimester patient plasma with Raman spectroscopy and protein analysis — Bioengineering & translational medicine (2024)
Metabolic response to small molecule therapy in colorectal cancer tracked with Raman spectroscopy and metabolomics — Angewandte Chemie International Edition (2024)
Dimat: Decentralized iterative merging-and-training for deep learning models — Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern … (2024)
First trimester prediction of preterm birth in patient plasma with machine-learning-guided Raman spectroscopy and metabolomics — ACS applied materials & interfaces (2023)
Few-shot deep learning for AFM force curve characterization of single-molecule interactions — Patterns (2023)
Active shooter detection and robust tracking utilizing supplemental synthetic data — arXiv preprint arXiv:2309.03381 (2023)
Deep learning for fast atomic force microscopy data analytics — Biophysical Journal (2021)
Fast inverse design of microstructures via generative invariance networks — Nature Computational Science (2021)

jrwaite (@) iastate.eduGoogle Scholar

Graduate Alumni

Hsin-Jung Yang

Ph.D., Mechanical Engineering, 2026

Joined Fall 2021

Ph.D., Mechanical Engineering, Iowa State University, 2026
M.S., Applied Mechanics, National Taiwan University, 2020
B.S., Engineering Science and Ocean Engineering, National Taiwan University, 2018

About

Hsin-Jung completed his Ph.D. in the Department of Mechanical Engineering at Iowa State University, defending in Summer 2026. He joined the Self-aware Complex Systems Laboratory in Fall 2021, where his research focused on machine learning, deep learning, mechatronics, and robotics. His other interests include hiking and photography.

Research interests: Machine learning, deep learning, mechatronics, robotics

Publications with the lab (9)

Enhancing PPO With Trajectory-Aware Hybrid Policies — IEEE Transactions on Neural Networks and Learning Systems (2026)
LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy — arXiv (2026)

Show all 9

Data-driven Kinematic Modeling in Soft Robots: System Identification and Uncertainty Quantification — 5th Modeling, Estimation and Control Conference (MECC 2025) (2025)
Find the fruit: Designing a zero-shot sim2real deep rl planner for occlusion aware plant manipulation — IEEE International Conference on Robotics and Automation (ICRA 2026), in press (2026)
Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms — Proceedings of the 7th Annual Learning for Dynamics & Control Conference (L4DC 2025), PMLR 283 (2025)
In the Mix: A Workshop Merging Computational Chemistry and Electrochemistry Alongside Data Science — Journal of chemical education (2024)
Persistent monitoring of insect-pests on sticky traps through hierarchical transfer learning and slicing-aided hyper inference — Frontiers in Plant Science (2024)
GENESIS-RL: GEnerating natural edge-cases with systematic integration of safety considerations and reinforcement learning — 2024 IEEE International Automated Vehicle Validation Conference (IAVVC) (2024)
Deep Reinforcement Learning for Robotic Control with Multi-Fidelity Models — IFAC-PapersOnLine (2022)

hjy (@) iastate.eduLinkedIn Google Scholar GitHub

Mahsa Khosravi

Ph.D., Industrial Engineering, 2026

Joined Summer 2021

Ph.D., Industrial Engineering, Iowa State University, 2026
M.S., Industrial Engineering, University of Tehran, Tehran, Iran, 2015
B.S., Industrial Engineering, Semnan University of Science and Technology, Semnan, Iran, 2013

About

Mahsa Khosravi completed her Ph.D. in Industrial Engineering at Iowa State University, defending in Fall 2026. She joined the Self-aware Complex Systems Laboratory in Summer 2021, where her research centered on reinforcement learning, machine learning, deep learning, and robotics. Her M.S. research focused on cancer diagnosis and recurrence prediction using machine learning. She also enjoys playing the piano, reading books, and rock climbing.

Research interests: Reinforcement learning, machine learning, deep learning, robotics

Publications with the lab (4)

Enhancing PPO With Trajectory-Aware Hybrid Policies — IEEE Transactions on Neural Networks and Learning Systems (2026)
Optimizing navigation and chemical application in precision agriculture with deep reinforcement learning and conditional action tree — Smart Agricultural Technology (2025)

Show all 4

Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms — Proceedings of the 7th Annual Learning for Dynamics & Control Conference (L4DC 2025), PMLR 283 (2025)
AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning — Computers and Electronics in Agriculture (2026)

mahsak (@) iastate.eduGoogle Scholar GitHub

Kin Gwn Lore

M.S. 2016

Now: AI/ML Specialist, Deloitte

M.S., Mechanical Engineering, Iowa State University, 2016
B.S., Mechanical Engineering, Iowa State University, 2014

About

Kin worked on multi-agent systems and applied machine learning to physical engineering problems. His projects covered network topology control in multi-agent proximity networks, deep learning for microfluidic pillar sculpting, low-light image enhancement (LLNet), decision-making in cyber-physical systems, and prognostics and health monitoring. He received the Iowa State University Graduate College Research Excellence Award in 2016. Outside research, he has a passion for creative work, from digital art and music to video editing and programming.

He graduated from the SCS Lab in December 2016 and joined United Technologies Research Center (later Raytheon Technologies Research Center) in East Hartford, CT, where he became a Principal Research Engineer in AI/ML. He is now an AI/ML Specialist at Deloitte.

Research interests: Machine learning, computer vision, low-light image enhancement, anomaly detection, predictive maintenance

Publications with the lab (17)

Root-cause analysis for time-series anomalies via spatiotemporal graphical modeling in distributed complex systems — Knowledge-Based Systems (2021)
A deep learning framework for causal shape transformation — Neural Networks (2018)

Show all 17

Deep Learning for Engineering Big Data Analytics — Big Data Analytics (2017)
Data-driven root-cause analysis for distributed system anomalies — (2017)
Deep learning for flow sculpting: Insights into efficient learning using scientific simulation data — Scientific reports (2017)
LLNet: A deep autoencoder approach to natural low-light image enhancement — Pattern Recognition (2017)
Deep Action Sequence Learning for Causal Shape Transformation — arXiv preprint arXiv:1605.05368 (2016)
Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes — arXiv preprint arXiv:1612.02141 (2016)
Early Detection of Combustion Instabilities using Deep Convolutional Selective Autoencoders on Hi-speed Flame Video — arXiv preprint arXiv:1603.07839 (2016)
A Deep 3D Convolutional Neural Network Based Design for Manufacturability Framework — arXiv preprint arXiv:1612.02141 (2016)
Deep value of information estimators for collaborative human-machine information gathering — 2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS … (2016)
Topology control in mobile sensor networks using information space feedback — (2016)
Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities — (2016)
Prognostics of combustion instabilities from hi-speed flame video using a deep convolutional selective autoencoder — International Journal of Prognostics and Health Management (2016)
Early Detection of Combustion Instability by Neural-Symbolic Analysis on Hi-Speed Video. — CoCo@ NIPS (2015)
Early detection of combustion instability from hi-speed flame images via deep learning and symbolic time series analysis — Annual Conference of the PHM Society (2015)
Hierarchical feature extraction for efficient design of microfluidic flow patterns — Feature Extraction: Modern Questions and Challenges (2015)

kglore (@) iastate.eduGoogle Scholar Homepage GitHub Google Scholar

Kundan Kumar

M.S. 2016 · Ph.D. 2026, Computer Science, Iowa State University

Now: AI Safety Research Fellow, Algoverse

Ph.D., Computer Science (minor in Statistics), Iowa State University, 2026
M.S., Computer Science, Iowa State University, 2016
B.Tech., Electronics and Communication Engineering, 2012

About

A mysterious student who showed up in the lab only late at night and on weekends. Even his profile picture was mysterious!

After his M.S., Kundan stayed at Iowa State for a Ph.D. in Computer Science with a minor in Statistics, advised by Dr. Christopher Quinn and Dr. Ravikumar Gelli, and defended his dissertation in June 2026. He is now an AI Safety Research Fellow at Algoverse, working on AI evaluations, adversarial robustness, scalable oversight, and LLM reasoning and agents.

Research interests: AI safety and alignment, adversarial robustness, LLM reasoning and agents, autonomous perception and control

Publications with the lab (1)

Deep value of information estimators for collaborative human-machine information gathering — 2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS … (2016)

kkumar (@) iastate.eduHomepage Google Scholar Faculty page

Vikas Chawla

M.S. 2016 · Senior Software Engineer, Twilio

Now: Senior Software Engineer, Twilio

M.S., Computer Science, Iowa State University, 2016

About

Vikas completed his M.S. in Computer Science at Iowa State University in 2016. He went on to work at Twilio as a Senior Software Engineer.

Publications with the lab (2)

An end-to-end convolutional selective autoencoder approach to Soybean Cyst Nematode eggs detection — arXiv preprint arXiv:1603.07834 (2016)
A bayesian network approach to county-level corn yield prediction using historical data and expert knowledge — Iowa State University (2016)

vchawla (@) iastate.edu

Adedotun Akintayo

Ph.D. 2017

Joined Fall 2014Now: The Boeing Company

Ph.D., Mechanical Engineering, Iowa State University, 2017
M.S., Control Systems, University of Sheffield, United Kingdom, 2014
B.E., Mechanical Engineering, Ahmadu Bello University, Zaria, Nigeria, 2009

About

Adedotun was a Ph.D. student in the Department of Mechanical Engineering and joined Dr. Soumik Sarkar's lab in Fall 2014. His research interests included data and systems modeling, computational intelligence, active energy control in buildings, optimization, and combinatorics. He likes driving around town, meeting people, and reading.

He graduated from the SCS Lab in December 2017 and worked at Intel as a Graphics Software Engineer in Folsom, CA. He is now with The Boeing Company.

Research interests: Applied machine and deep learning for complex systems analysis, data and systems modeling, building energy control, optimization

Publications with the lab (13)

3D convolutional selective autoencoder for instability detection in combustion systems — Energy and AI (2021)
Building Energy Disaggregation using Spatiotemporal Pattern Network — (2018)

Show all 13

Hierarchical symbolic dynamic filtering of streaming non-stationary time series data — Signal Processing (2018)
Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network — Applied Energy (2018)
A deep learning framework to discern and count microscopic nematode eggs — Scientific reports (2018)
Energy prediction using spatiotemporal pattern networks — Applied Energy (2017)
High speed video-based health monitoring using 3D deep learning — Dynamic Data-Driven Application Systems (DDDAS) (2017)
LLNet: A deep autoencoder approach to natural low-light image enhancement — Pattern Recognition (2017)
An end-to-end convolutional selective autoencoder approach to Soybean Cyst Nematode eggs detection — arXiv preprint arXiv:1603.07834 (2016)
Early Detection of Combustion Instabilities using Deep Convolutional Selective Autoencoders on Hi-speed Flame Video — arXiv preprint arXiv:1603.07839 (2016)
Probabilistic Graphical Modeling of Distributed Cyber-Physical Systems — Elsevier eBooks (2016)
Prognostics of combustion instabilities from hi-speed flame video using a deep convolutional selective autoencoder — International Journal of Prognostics and Health Management (2016)
A Symbolic Dynamic Filtering approach to unsupervised hierarchical feature extraction from time-series data — (2015)

akintayo (@) iastate.eduGoogle Scholar

Linjiang Wu

M.S. 2018

Now: Sr. System Engineer (Architect), Continental

M.S., Mechanical Engineering, Iowa State University, 2018
B.S., Automotive Engineering, Wuhan University of Technology, 2012

About

Linjiang worked on graphical modeling of cyber-physical systems for engineering problems. His studies covered traffic sensor health monitoring, building energy consumption analysis and prediction, and deep learning for feature extraction and fault detection. He has a passion for automotive engineering and is an experienced automotive engineer.

He graduated from the SCS Lab in May 2018 and worked at Hi-Lex Controls Inc. in Rochester Hills, MI. He is now a Sr. System Engineer (Architect) at Continental, working on AR head-up displays.

Research interests: AR head-up displays, machine learning, data mining, fault diagnosis

Publications with the lab (5)

Crop yield prediction integrating genotype and weather variables using deep learning — Plos one (2021)
Traffic sensor health monitoring using spatiotemporal graphical modeling — International Journal of Prognostics and Health Management (2020)

Show all 5

An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems — Mechanical Systems and Signal Processing (2019)
A Data-driven Approach towards Integration of Microclimate Conditions for Predicting Building Energy Performance — 5th International High Performance Buildings Conference (2018)
Linked read technology for assembling large complex and polyploid genomes — BMC genomics (2018)

lwu26 (@) iastate.eduGoogle Scholar

Apurva Kokate

M.S. 2018

Joined Spring 2017Now: Oregon State University

M.S., Computer Science, Iowa State University, 2018
B.E., Computer Engineering, University of Mumbai, 2016

About

Apurva joined the lab in Spring 2017. She has a passion for computer science, especially solving puzzles and developing programs, and cares about using technology responsibly and ethically. She hoped to help make machines more intelligent and to push AI forward. In the lab, she worked with machine learning techniques; her M.S. thesis was "A study of interpretability mechanisms for deep networks" (2018).

She graduated from the SCS Lab in May 2018 and worked at Kingland Systems as a Software Designer. She is now affiliated with Oregon State University.

Research interests: Machine learning, interpretability of deep networks

Publications with the lab (2)

Interpretable deep learning for guided microstructure-property explorations in photovoltaics — npj Computational Materials (2019)
A forward-backward approach for visualizing information flow in deep networks — NIPS 2017 Symposium on Interpretable Machine Learning (2017)

Google Scholar

Venkatesh Chinde

Ph.D., Mechanical Engineering

Now: Research Engineer, National Renewable Energy Laboratory (NREL)

Ph.D., Mechanical Engineering (minor in Mathematics), Iowa State University
M.S., Electrical and Computer Engineering, Iowa State University, 2015
M.Tech., Electrical and Electronics Engineering, VJTI, 2010
B.S., Electrical and Electronics Engineering, Auroras Engineering College, 2008

About

Venkatesh was a Ph.D. student in the Department of Mechanical Engineering. His research interests included building control systems, distributed optimization, diffusion maps, passivity-based control, flatness-based control, and feedback linearization. He enjoys badminton, tennis, and cooking.

He completed his Ph.D. in Mechanical Engineering, with a minor in Mathematics, at Iowa State University and is now a Research Engineer at the National Renewable Energy Laboratory (NREL).

Research interests: Building control systems, distributed optimization, passivity-based control, flatness-based control, feedback linearization

Publications with the lab (7)

Supervisory control and distributed optimization of building energy systems — Journal of Dynamic Systems, Measurement, and Control (2020)
A Data-driven Approach towards Integration of Microclimate Conditions for Predicting Building Energy Performance — 5th International High Performance Buildings Conference (2018)

Show all 7

A passivity-based power-shaping control of building HVAC systems — Journal of Dynamic Systems, Measurement, and Control (2017)
Scalable supervisory control of building energy systems using generalized gossip — 2016 American Control Conference (ACC) (2016)
Building HVAC systems control using power shaping approach — (2016)
A volttron based implementation of supervisory control using generalized gossip for building energy systems — (2016)
Comparative evaluation of control-oriented zone temperature prediction modeling strategies in buildings — Dynamic Systems and Control Conference 57250, V002T34A009 (2015)

vchinde (@) iastate.eduPersonal Website Google Scholar

Shuo Wang

Ph.D. 2018 · Senior Systems Engineer, NVIDIA

Now: Senior Systems Engineer, NVIDIA

Ph.D., Civil Engineering, Iowa State University, 2018
M.S., Civil Engineering, University of Nebraska–Lincoln, 2014

About

Shuo completed his Ph.D. in Civil Engineering at Iowa State University in 2018. He works on intelligent transportation systems, smart cities, and intelligent video analysis, and is now a Senior Systems Engineer at NVIDIA in Santa Clara, CA.

Research interests: Intelligent transportation systems, smart city, intelligent video analysis

Google Scholar

Zhanhong Jiang

Ph.D. 2018

Joined Fall 2014Now: Data Scientist, Translational AI Center (TrAC), Iowa State University

Ph.D., Mechanical Engineering, Iowa State University, 2018
M.S., Mechanical Engineering, Chinese Academy of Sciences, 2014
B.E., Mechanical Engineering, Shenzhen University, 2011

About

Zhanhong joined the lab in Fall 2014. His research focused on cyber-physical systems, multi-agent systems, system dynamics, and optimization. In his free time, he enjoys tennis, cooking, and reading.

He graduated from the SCS Lab in December 2018 and worked as a Data Scientist at Johnson Controls in Milwaukee, WI. He has since returned to Iowa State University as a Data Scientist at the Translational AI Center (TrAC), working on distributed optimization and machine learning.

Research interests: Distributed optimization, machine learning, cyber-physical systems, multi-agent systems

Publications with the lab (58)

DeCAF: Decentralized consensus-and-factorization for low-rank adaptation of foundation models — Neural Networks (2026)
ADKO: Agentic Decentralized Knowledge Optimization — arXiv (2026)

Show all 58

Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting — SSRN Electronic Journal (2026)
Personalized Federated Direct Preference Optimization via LoRA Adapters — arXiv (2026)
TabQL: In-Context Q-Learning with Tabular Foundation Models — arXiv (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)
Enhancing PPO With Trajectory-Aware Hybrid Policies — IEEE Transactions on Neural Networks and Learning Systems (2026)
LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy — arXiv (2026)
Optimizing navigation and chemical application in precision agriculture with deep reinforcement learning and conditional action tree — Smart Agricultural Technology (2025)
Data-driven Kinematic Modeling in Soft Robots: System Identification and Uncertainty Quantification — 5th Modeling, Estimation and Control Conference (MECC 2025) (2025)
Automated Seizure Detection in Animal EEG Signals — bioRxiv (Cold Spring Harbor Laboratory), Cold Spring Harbor Laboratory (2025)
Decentralized relaxed smooth optimization with gradient descent methods — arXiv preprint arXiv:2508.08413 (2025)
RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception — Proceedings of the ACM/IEEE 16th International Conference on Cyber-Physical … (2025)
Neural CDEs as Correctors for Learned Time Series Models — arXiv (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)
A unified convergence theory for large language model efficient fine-tuning — OPT 2024: Optimization for Machine Learning (2024)
STITCH: Surface reconstrucTion using Implicit neural representations with Topology Constraints and persistent Homology — arXiv preprint arXiv:2412.18696 (2024)
Fawac: Feasibility informed advantage weighted regression for persistent safety in offline reinforcement learning — arXiv preprint arXiv:2412.08880 (2024)
Latent safety-constrained policy approach for safe offline reinforcement learning — International Conference on Learning Representations (ICLR 2025) (2025)
Dominating Set Model Aggregation for communication-efficient decentralized deep learning — Neural Networks (2024)
Neural pde solvers for irregular domains — Computer-Aided Design (2024)
The stochastic augmented lagrangian method for domain adaptation — Knowledge-Based Systems (2022)
Asynchronous training schemes in distributed learning with time delay — arXiv preprint arXiv:2208.13154 (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)
On consensus-optimality trade-offs in collaborative deep learning — Frontiers in artificial intelligence (2021)
Root-cause analysis for time-series anomalies via spatiotemporal graphical modeling in distributed complex systems — Knowledge-Based Systems (2021)
Decentralized Deep Learning Using Momentum-Accelerated Consensus — Preprint (2021)
Cross-gradient aggregation for decentralized learning from non-iid data — International conference on machine learning (2021)
Spatiotemporal attention for multivariate time series prediction and interpretation — ICASSP 2021-2021 IEEE international conference on acoustics, speech and … (2021)
Data-Driven Performance Monitoring of Dynamical Systems Using Granger Causal Graphical Models — Journal of Dynamic Systems Measurement and Control (2020)
Interpretable Deep Attention Model for Multivariate Time Series Prediction in Building Energy Systems — Lecture notes in computer science (2020)
Supervisory control and distributed optimization of building energy systems — Journal of Dynamic Systems, Measurement, and Control (2020)
On higher-order moments in adam — Beyond First Order Methods in Machine Learning Workshop, NeurIPS 2019 (2019)
Learning State Switching for Improved Exploration in Multi-sensor Environments — (2019)
Learning State Switching for Multi-sensor Integration — (2019)
Generalised gossip-based subgradient method for distributed optimisation — International Journal of Control (2019)
Exploring Granger causality in dynamical systems modeling and performance monitoring — 2018 IEEE Conference on Decision and Control (CDC) (2018)
On consensus-disagreement tradeoff in distributed optimization — 2018 Annual American Control Conference (ACC) (2018)
Hierarchical Optimization for Building Energy Systems — (2018)
Building Energy Disaggregation using Spatiotemporal Pattern Network — (2018)
Online robust policy learning in the presence of unknown adversaries — Advances in neural information processing systems (2018)
Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network — Applied Energy (2018)
Convergence and noise effect analysis for generalized gossip-based distributed optimization — 2017 American Control Conference (ACC) (2017)
Autonomous Mobile Sensing Platform for Spatio-Temporal Plant Phenotyping — (2017)
Energy prediction using spatiotemporal pattern networks — Applied Energy (2017)
An unsupervised anomaly detection approach using energy-based spatiotemporal graphical modeling — Cyber-physical systems (2017)
Collaborative deep learning in fixed topology networks — Advances in Neural Information Processing Systems (2017)
Scalable supervisory control of building energy systems using generalized gossip — 2016 American Control Conference (ACC) (2016)
An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed cps — 2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS … (2016)
Probabilistic Graphical Modeling of Distributed Cyber-Physical Systems — Elsevier eBooks (2016)
A volttron based implementation of supervisory control using generalized gossip for building energy systems — (2016)
Comparative evaluation of control-oriented zone temperature prediction modeling strategies in buildings — Dynamic Systems and Control Conference 57250, V002T34A009 (2015)
Understanding Wind Turbine Interactions Using Spatiotemporal Pattern Network — (2015)
On distributed optimization using generalized gossip — (2015)

zhjiang (@) iastate.eduGoogle Scholar Faculty page

Sambuddha Ghosal

Ph.D. 2019

Joined Fall 2015Now: Senior Research Data Scientist, Bayer R&D

Ph.D., Mechanical Engineering, Iowa State University, 2019
M.S., Computer Science, Iowa State University, 2019
M.S., Mechanical Engineering, Iowa State University, 2017
B.E., Mechanical Engineering, Jadavpur University, 2015

About

Sambuddha joined the lab in Fall 2015. His research interests included control systems, cyber-physical systems, dynamics and optimization, and deep and machine learning. His work included anomaly detection in large-scale cyber-physical systems and the use of sparsity-promoting dynamic mode decomposition to extract characteristic features and dynamics of complex fluid flows (e.g., combustion flames) from snapshot data. His doctoral work led to a first-author paper in the Proceedings of the National Academy of Sciences (PNAS). He enjoys playing piano and chess, biking, and shooting.

He graduated from the SCS Lab in 2019 and was a Postdoctoral Associate at the MIT Media Lab, advised by Dr. Pratik Shah. He is now a Senior Research Data Scientist at Bayer R&D.

Research interests: Machine learning, deep learning, computer vision, generative AI, neural network interpretability

Publications with the lab (14)

Deep Multiview Image Fusion for Soybean Yield Estimation in Breeding Applications — Plant Phenomics (2021)
Encoding Invariances in Deep Generative Models — arXiv preprint arXiv:1906.01626 (2019)

Show all 14

Generative models for solving nonlinear partial differential equations — Proc. of NeurIPS Workshop on ML for Physics (2019)
Binary 2d morphologies of polymer phase separation: Dataset and python toolbox — (2019)
Interpretable deep learning for guided microstructure-property explorations in photovoltaics — npj Computational Materials (2019)
A weakly supervised deep learning framework for sorghum head detection and counting — Plant Phenomics, AAAS (2019)
An explainable deep machine vision framework for plant stress phenotyping — Proceedings of the National Academy of Sciences (2018)
NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images — (2018)
Interpretable Deep Learning applied to Plant Stress Phenotyping — arXiv preprint arXiv:1710.08619 (2017)
High speed video-based health monitoring using 3D deep learning — Dynamic Data-Driven Application Systems (DDDAS) (2017)
An unsupervised anomaly detection approach using energy-based spatiotemporal graphical modeling — Cyber-physical systems (2017)
Data-driven persistent monitoring of Indoor Air Systems — Iowa State University Digital Repository (Iowa State University), Iowa State University (2016)
Detection and analysis of combustion instability from hi-speed flame images using dynamic mode decomposition — Dynamic Systems and Control Conference 50695, V001T12A005 (2016)
An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed cps — 2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS … (2016)

sghosal (@) iastate.eduGoogle Scholar Homepage GitHub

Truong Tran

M.S. 2019, Mechanical Engineering

Joined Fall 2017Now: Security Analyst, VinCSS

M.S., Mechanical Engineering, Iowa State University, 2019
B.E., Mechanical Engineering, Hanoi University of Science and Technology, 2017

About

Truong joined the lab in Fall 2017. His research interests were computer vision, robotics, and software engineering. He has experience with embedded computer vision systems (C++ with the Qt framework) and with hardware-accelerated machine learning on GPU clusters (TensorFlow) and mobile devices (Apple Core ML). In the lab, he applied machine learning to plant science and worked on 3D reconstruction of plants using mobile devices. He was an Erasmus Mundus Scholar in 2015–2016. In his free time, Truong enjoys photography and reading novels.

He graduated from the SCS Lab in December 2019 and went on to work as a Security Analyst at VinCSS.

Research interests: Computer vision, robotics, software engineering, machine learning for plant science

Publications with the lab (1)

Soybean Root Phenomics — Iowa State University Research and Demonstration Farms Progress Reports (2019)

txtran (@) iastate.eduLinkedin

Zhisheng Zhang

M.S. 2019 · Image Data Scientist, Bayer Crop Science

Joined Spring 2017Now: Image Data Scientist, Bayer Crop Science

M.S., Mechanical Engineering, Iowa State University, 2019
B.S., Mechanical Engineering, Iowa State University, 2016

About

Zhisheng joined the lab in Spring 2017. His research interests were deep learning and machine learning applications to engineering problems. In the lab, he worked on deep learning for plant science and agriculture, based on object classification, localization, and detection.

He graduated from the SCS Lab in July 2019 and went on to work at Bayer Crop Science in St. Louis, MO, as an Image Data Scientist.

Research interests: Deep learning, machine learning, object detection for plant science and agriculture

Publications with the lab (1)

Deep Multiview Image Fusion for Soybean Yield Estimation in Breeding Applications — Plant Phenomics (2021)

zhisheng (@) iastate.edu

Ameya Joshi

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

About

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)

Show all 17

NeuFENet: neural finite element solutions with theoretical bounds for parametric PDEs — Engineering with Computers (2024)
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 Website Google Scholar GitHub

Amitangshu Mukherjee

M.S. 2020

Joined Fall 2018Now: Ph.D. Candidate, Electrical and Computer Engineering, Purdue University

M.S., Computer Engineering, Iowa State University, 2020
B.Tech., Applied Electronics and Instrumentation Engineering, Heritage Institute of Technology, Kolkata, 2016

About

Amitangshu was a graduate student in the Department of Electrical and Computer Engineering at Iowa State University, jointly supervised by Prof. Chinmay Hegde and Prof. Soumik Sarkar. During his undergraduate studies, he completed industrial internships at Indian Oil Corporation Ltd. and Siemens India Pvt. Ltd., and in summer 2015 he was a summer research intern at the New Jersey Institute of Technology. He joined Dr. Soumik Sarkar's lab in Fall 2018, where his research interests included deep learning, computer vision, generative modeling, and adversarial learning, with applications to autonomous vehicles. His other interests include traveling, playing soccer and table tennis, hiking, and reading comics.

He graduated with an M.S. in Computer Engineering in Fall 2019 and is now a Ph.D. candidate in Electrical and Computer Engineering at Purdue University, working with Prof. Kaushik Roy in the Nano(Neuro) Electronics Research Laboratory. His current research focuses on scene understanding, robust deep learning, and multimodal models.

Research interests: Scene understanding, robust deep learning, multimodal models

Publications with the lab (4)

Generative semantic domain adaptation for perception in autonomous driving — Journal of big data analytics in transportation (2022)
Semantic domain adaptation for deep classifiers via gan-based data augmentation — Proc. Conf. Neural Inf. Process. Syst. Workshops (2019)

Show all 4

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)

amimukh (@) iastate.eduHomepage Google Scholar GitHub

Sambit Ghadai

Ph.D. 2020

Joined Fall 2016Now: Graphics Software Engineer, Intel

Ph.D., Mechanical Engineering (co-major: Computer Engineering), Iowa State University, 2020
B.Tech., Industrial and Product Design, NIT Rourkela, 2015

About

Sambit joined the lab in Fall 2016. His research interests included cyber-physical systems, cyber-manufacturing, computational geometry, GPU computing, and visualization. He has a keen interest in playing musical instruments and loves to travel and read.

He graduated from the SCS Lab in July 2020 and is currently a Graphics Software Engineer at Intel.

Research interests: Cyber-physical systems, cyber-manufacturing, computational geometry, GPU computing, visualization

Publications with the lab (10)

Multi-resolution 3D CNN for learning multi-scale spatial features in CAD models — Computer Aided Geometric Design (2021)
A Machine Learning Framework for Decision Support in Design and Manufacturing — ASME eBooks (2021)

Show all 10

Orthogonal distance fields representation for machine-learning based manufacturability analysis — International Design Engineering Technical Conferences and Computers and … (2020)
Spatiotemporally constrained action space attacks on deep reinforcement learning agents — Proceedings of the AAAI conference on artificial intelligence (2020)
Multi-Level 3D CNN for Learning Multi-Scale Spatial Features — CVPR 2019 Workshop on Deep Learning for Geometric Shape Understanding (2019)
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)
Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes — arXiv preprint arXiv:1612.02141 (2016)

sambitg (@) iastate.eduGoogle Scholar

Homagni Saha

Ph.D. 2021 · Computer Vision Engineer, Danfoss Power Solutions (as listed)

Joined Fall 2016Now: Computer Vision Engineer, Danfoss Power Solutions

Ph.D., Mechanical Engineering, Iowa State University, 2021
M.S., Computer Science, Iowa State University, 2021
M.S., Mechanical Engineering, Iowa State University, 2018
B.Tech., Mechanical Engineering, NIT Rourkela, 2016

About

Homagni joined the lab in Fall 2016. His research interests included probabilistic graphical modeling, reinforcement learning, and anomaly detection. He has a burning passion for robotics and was the go-to person for any robotics project in the lab. He worked on the design and control of agricultural robots, human-computer interaction for the TurtleBot, and visuomotor control of the one-armed Sawyer robot.

He graduated from the SCS Lab in May 2021 and then joined Danfoss Power Solutions as a Computer Vision Engineer. His recent work spans vision-language models, multimodal representation learning, efficient ML, robotics, and cyber-physical systems.

Research interests: Vision-language models, multimodal representation learning, efficient ML, robotics, cyber-physical systems

Publications with the lab (17)

Few-shot deep learning for AFM force curve characterization of single-molecule interactions — Patterns (2023)
A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment — Frontiers in Robotics and AI (2022)

Show all 17

Multimodal sensor fusion framework for residential building occupancy detection — Energy and buildings (2022)
Few shot clustering for indoor occupancy detection with extremely low quality images from battery free cameras — Iowa State University (2021)
Whisper: wireless home identification and sensing platform for energy reduction — Journal of Sensor and Actuator Networks (2021)
Battery-free camera occupancy detection system — Proceedings of the 5th international workshop on embedded and mobile deep … (2021)
Data-Driven Performance Monitoring of Dynamical Systems Using Granger Causal Graphical Models — Journal of Dynamic Systems Measurement and Control (2020)
Granger causality based hierarchical time series clustering for state estimation — IFAC-PapersOnLine (2020)
A perspective on multi-agent communication for information fusion — NeurIPS 2019 Workshop on Visually Grounded Interaction and Language (2019)
For publication in 2019 acc a flexible framework for building occupancy detection using spatiotemporal pattern networks — 2019 American Control Conference (ACC) (2019)
Learning State Switching for Improved Exploration in Multi-sensor Environments — (2019)
Learning State Switching for Multi-sensor Integration — (2019)
Occupancy sensing in buildings: A review of data analytics approaches — Energy and Buildings 188 (2019)
Exploring Granger causality in dynamical systems modeling and performance monitoring — 2018 IEEE Conference on Decision and Control (CDC) (2018)
Navigation Strategies for a Multi-Robot Ground-Based Row Crop Phenotyping Platform — (2018)
A novel multirobot system for plant phenotyping — Robotics (2018)
Autonomous Mobile Sensing Platform for Spatio-Temporal Plant Phenotyping — (2017)

hsaha (@) iastate.eduPersonal Website LinkedIn Google Scholar GitHub

Jaydeep-Ravindra Rade

M.S. 2021

Joined Spring 2019Now: Research Scientist – AI, GE Vernova Advanced Research Center

M.S., Electrical Engineering, Iowa State University, 2021
B.Tech., Electronics Engineering, Veermata Jijabai Technological Institute (VJTI), Mumbai, 2018

About

Jaydeep joined the lab in Spring 2019, co-advised by Dr. Soumik Sarkar and Dr. Adarsh Krishnamurthy. His research interests were deep learning, image processing, and their applications, and he worked on deep learning for topology optimization; his M.S. thesis was titled "Deep Learning Frameworks for Structural Topology Optimization." Outside of academics, he enjoys music, cooking, and traveling.

He graduated from the SCS Lab in December 2020 and continued as a Ph.D. student in Electrical Engineering at Iowa State University under Dr. Adarsh Krishnamurthy and Dr. Anwesha Sarkar, working on 3D deep learning, including protein structure reconstruction from AFM images. He is currently a Research Scientist – AI at the GE Vernova Advanced Research Center.

Research interests: Deep learning, computer vision, 3D computer vision, AI for engineering

Publications with the lab (11)

In-context adaptation of VLMs for few-shot cell detection in optical microscopy — Frontiers in Artificial Intelligence (2026)
BPS2026 – In-context adaptation of vision language models (VLMs) for few-shot cell detection in microscopy — Biophysical Journal (2026)

Show all 11

Conversational LLM-based decision support for defect classification in AFM images — IEEE Open Journal of Instrumentation and Measurement, IEEE (2025)
Latent diffusion models for structural component design — Computer-Aided Design (2024)
3d reconstruction of protein structures from multi-view afm images using neural radiance fields (nerfs) — Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern … (2024)
Deep learning-based 3D multigrid topology optimization of manufacturable designs — Engineering Applications of Artificial Intelligence (2023)
Deep learning for live cell shape detection and automated afm navigation — Bioengineering (2022)
3d reconstruction of protein complex structures using synthesized multi-view afm images — Machine Learning for Structural Biology Workshop, NeurIPS 2022 (2022)
AI guided measurement of live cells using AFM — IFAC-PapersOnLine (2021)
Algorithmically-consistent deep learning frameworks for structural topology optimization — Engineering Applications of Artificial Intelligence (2021)
Multigrid Distributed Deep CNNs for Structural Topology Optimization — AAAI 2022 Workshop on AI for Design and Manufacturing (ADAM) (2021)

jrrade (@) iastate.eduHomepage Google Scholar GitHub

Yasaman Esfandiari

Ph.D. 2021

Joined Fall 2018Now: HRL Laboratories

Ph.D., Mechanical Engineering, Iowa State University, 2021
M.S., Mechanical Engineering, Iowa State University, 2017
B.S., Mechanical Engineering, Amirkabir University of Technology, Tehran, Iran, 2015

About

Yasaman was a Ph.D. student in Mechanical Engineering and joined the lab in Fall 2018. Her research interests were dynamics and controls, optimization, machine learning, and deep learning. She worked on nonconvex robust optimization in deep neural networks with unknown adversaries. Her other activities include playing piano, reading, and working out.

She graduated from the SCS Lab in 2021 and is currently working at HRL Laboratories.

Research interests: Dynamics and controls, optimization, machine learning, deep learning

Publications with the lab (6)

Dominating Set Model Aggregation for communication-efficient decentralized deep learning — Neural Networks (2024)
A fast saddle-point dynamical system approach to robust deep learning — Neural Networks (2021)

Show all 6

Distributed deep learning for persistent monitoring of agricultural fields — NeurIPS 2021 AI for science workshop (2021)
Query-based targeted action-space adversarial policies on deep reinforcement learning agents — Proceedings of the ACM/IEEE 12th international conference on cyber-physical … (2021)
Cross-gradient aggregation for decentralized learning from non-iid data — International conference on machine learning (2021)
Robustifying reinforcement learning agents via action space adversarial training — 2020 American control conference (ACC) (2020)

yasesf (@) iastate.eduGoogle Scholar

Koushik Nagasubramanian

Ph.D. 2021

Now: Deep Learning Scientist, Bayer Crop Science

Ph.D., Electrical Engineering, Iowa State University, 2021
B.Tech., Electronics and Communication Engineering, RNSIT, Bangalore, India, 2015

About

Koushik was a Ph.D. student jointly supervised by Prof. Baskar Ganapathysubramanian and Prof. Soumik Sarkar. After receiving his undergraduate degree in 2015, he worked at Nubesol Technologies, Bangalore, for about seven months. His research interests included machine learning, deep learning, and computer vision, and he worked on deep learning for plant disease prediction.

He graduated from the SCS Lab in June 2021 and is currently a Deep Learning Scientist at Bayer Crop Science.

Research interests: Machine learning, deep learning, computer vision

Publications with the lab (20)

Cyber-agricultural systems for crop breeding and sustainable production — Trends in Plant Science 29 (2) (2024)
Self‐supervised learning improves classification of agriculturally important insect pests in plants — The Plant Phenome Journal (2023)

Show all 20

Plant phenotyping with limited annotation: Doing more with less — The Plant Phenome Journal (2022)
Privacy-preserving deep models for plant stress phenotyping — AI for Agriculture and Food Systems (2022)
Self-supervised agricultural insect pest classification — Authorea Preprints, Authorea (2022)
Exploring the use of 3d point cloud data for improved plant stress rating — AI for agriculture and food systems (2021)
Self-supervised learning improves agricultural pest classification — AI for agriculture and food systems (2021)
How useful is active learning for image‐based plant phenotyping? — The Plant Phenome Journal (2021)
High-throughput phenotyping in soybean — High-throughput crop phenotyping (2021)
Challenges and opportunities in machine-augmented plant stress phenotyping — Trends in Plant Science 26 (1) (2021)
Distributed deep learning for persistent monitoring of agricultural fields — NeurIPS 2021 AI for science workshop (2021)
Usefulness of interpretability methods to explain deep learning based plant stress phenotyping — arXiv preprint arXiv:2007.05729 (2020)
Automated trichome counting in soybean using advanced image‐processing techniques — Applications in plant sciences (2020)
Soybean Root Phenomics — Iowa State University Research and Demonstration Farms Progress Reports (2019)
Plant disease identification using explainable 3D deep learning on hyperspectral images — Plant Methods (2019)
Development of optimized phenomic predictors for efficient plant breeding decisions using phenomic-assisted selection in soybean — Plant Phenomics, AAAS (2019)
Explaining hyperspectral imaging based plant disease identification: 3D CNN and saliency maps — arXiv preprint arXiv:1804.08831 (2018)
PIRM2018 challenge on spectral image super-resolution: methods and results — Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)
NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images — (2018)
Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean stems — Plant methods (2018)

koushikn (@) iastate.eduGoogle Scholar

Tryambak Gangopadhyay

Ph.D. 2021

Joined Fall 2017Now: Senior Applied Scientist, Generative AI, Amazon Web Services

Ph.D., Mechanical Engineering, Iowa State University, 2021
M.S., Mechanical Engineering, Iowa State University, 2019
B.E., Mechanical Engineering, Jadavpur University, 2017

About

Tryambak joined Dr. Soumik Sarkar's lab in Fall 2017. His research focused on designing deep learning algorithms for large-scale image/video data, multivariate time-series data, and text data, with applications in healthcare, agriculture, vision, and cyber-physical systems. He also pursued a concurrent master's degree in Computer Science. In summer 2019, as an intern in the Machine Learning group at Lawrence Livermore National Laboratory (LLNL), he developed deep learning fusion models for clinical prediction tasks using electronic health record datasets. His other interests are story writing, reading, sketching, and playing guitar.

He graduated from the SCS Lab in March 2021 and is currently a Senior Applied Scientist in Generative AI at Amazon Web Services.

Research interests: Generative AI, machine learning, deep learning, cyber-physical systems

Publications with the lab (17)

Deep Learning and Dynamic Mode Decomposition for Characterizing Combustion Instability — (2026)
Transformer model to determine spatio-temporal relationships of variables, and interpretability for soybean seed yield, oil, and protein prediction — Frontiers in Artificial Intelligence (2026)

Show all 17

An LSTM-based approach to detect transition to lean blowout in swirl-stabilized dump combustion systems — Energy and AI (2024)
A deep learning approach to detect lean blowout in combustion systems — arXiv preprint arXiv:2208.01871 (2022)
3D convolutional selective autoencoder for instability detection in combustion systems — Energy and AI (2021)
Crop yield prediction integrating genotype and weather variables using deep learning — Plos one (2021)
Cross-modal virtual sensing for combustion instability monitoring — arXiv preprint arXiv:2110.01659 (2021)
Spatiotemporal attention for multivariate time series prediction and interpretation — ICASSP 2021-2021 IEEE international conference on acoustics, speech and … (2021)
Interpreting the impact of weather on crop yield using attention — NeurIPS Workshop on AI for Earth Sciences (2020)
Interpretable Deep Attention Model for Multivariate Time Series Prediction in Building Energy Systems — Lecture notes in computer science (2020)
Interpretable Deep Learning for Monitoring Combustion Instability — IFAC-PapersOnLine (2020)
An explainable framework using deep attention models for sequential data in combustion systems — NeurIPS 2019 workshop on machine learning and the physical sciences. NeurIPS (2019)
Deep time series attention models for crop yield prediction and insights — NeurIPS Workshop on Machine Learning and the Physical Sciences (2019)
Deep learning algorithms for detecting combustion instabilities — Dynamics and Control of Energy Systems (2019)
Characterizing Combustion Instability Using Deep Convolutional Neural Network — (2018)
Mode decomposition and convolutional neural network analysis of thermoacoustic instabilities in a rijke tube — (2018)
Temporal attention and stacked LSTMs for multivariate time series prediction — (2018)

tryambak (@) iastate.eduLinkedIn Google Scholar

Bernard Lee Xian Yeow

Ph.D. 2022

Now: Hitachi America, Ltd.

Ph.D., Mechanical Engineering, Iowa State University, 2022
B.S., Mechanical Engineering, Iowa State University, 2016

About

Xian Yeow received his bachelor's degree in Mechanical Engineering from Iowa State University in 2016 and went on to pursue his Ph.D. at Iowa State. His research interests included applications of deep reinforcement learning and deep generative methods for the robust and efficient design of cyber-physical systems.

He graduated in May 2022 and is currently working at Hitachi America, Ltd.

Research interests: Deep reinforcement learning, deep generative methods, robust and efficient design of cyber-physical systems

Publications with the lab (21)

A study of natural robustness of deep reinforcement learning algorithms towards adversarial perturbations — AI Open (2024)
Deep Reinforcement Learning for Robotic Control with Multi-Fidelity Models — IFAC-PapersOnLine (2022)

Show all 21

Multi-fidelity machine learning models for structure–property mapping of organic electronics — Computational Materials Science (2022)
A graph policy network approach for volt-var control in power distribution systems — Applied Energy (2022)
Generative design of material microstructures for organic solar cells using diffusion models — AI for Accelerated Materials Design NeurIPS 2022 Workshop (2022)
Distributed online non-convex optimization with composite regret — 2022 58th Annual Allerton Conference on Communication, Control, and … (2022)
Stochastic conservative contextual linear bandits — 2022 IEEE 61st Conference on Decision and Control (CDC) (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)
Fast inverse design of microstructures via generative invariance networks — Nature Computational Science (2021)
Inverse design of microstructures via generative networks for organic solar cells — AAAI 2022 Workshop on AI for Design and Manufacturing (ADAM) (2021)
Query-based targeted action-space adversarial policies on deep reinforcement learning agents — Proceedings of the ACM/IEEE 12th international conference on cyber-physical … (2021)
Robustifying reinforcement learning agents via action space adversarial training — 2020 American control conference (ACC) (2020)
Spatiotemporally constrained action space attacks on deep reinforcement learning agents — Proceedings of the AAAI conference on artificial intelligence (2020)
Differentiable programming for piecewise polynomial functions — (2020)
Two Photon lithography additive manufacturing: Video dataset of parameter sweep of light dosages, photo-curable resins, and structures — Data in Brief (2020)
Automated detection of part quality during two-photon lithography via deep learning — Additive Manufacturing (2020)
Multi-Level 3D CNN for Learning Multi-Scale Spatial Features — CVPR 2019 Workshop on Deep Learning for Geometric Shape Understanding (2019)
Learning to cope with adversarial attacks — arXiv preprint arXiv:1906.12061 (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)

xylee (@) iastate.eduLinkedIn Google Scholar

Russell Kai Liang Tan

Ph.D. 2022

Joined Spring 2018Now: GPU Software Development Engineer, Intel

Ph.D., Mechanical Engineering, Iowa State University, 2022
B.S., Mechanical Engineering, Iowa State University, 2017

About

Kai Liang (Russell) joined the Self-aware Complex Systems Lab in Spring 2018 after receiving his undergraduate degree from Iowa State University in Fall 2017. During his undergraduate studies, he interned at the Bobcat Company and Danfoss Power Solutions. His research interests included using deep learning, reinforcement learning, and computer vision to solve problems in engineering, cyber-physical systems, and autonomous systems. His creativity extends beyond academics to photography, digital art, and strategy video games.

He graduated from the SCS Lab in August 2022 and is currently a GPU Software Development Engineer at Intel.

Research interests: Deep learning, reinforcement learning, computer vision

Publications with the lab (8)

AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning — Computers and Electronics in Agriculture (2026)
Roadway weather challenges illuminate real‐world driving biomarkers of dementia risk — Alzheimer's & Dementia (2023)

Show all 8

MDPGT: momentum-based decentralized policy gradient tracking — Proceedings of the AAAI conference on artificial intelligence (2022)
Query-based targeted action-space adversarial policies on deep reinforcement learning agents — Proceedings of the ACM/IEEE 12th international conference on cyber-physical … (2021)
Robustifying reinforcement learning agents via action space adversarial training — 2020 American control conference (ACC) (2020)
Spatiotemporally constrained action space attacks on deep reinforcement learning agents — Proceedings of the AAAI conference on artificial intelligence (2020)
Robust deep reinforcement learning for traffic signal control — Journal of Big Data Analytics in Transportation (2020)
Deep reinforcement learning for adaptive traffic signal control — Dynamic systems and control conference 59162, V003T18A006 (2019)

kailiang (@) iastate.eduGoogle Scholar

Luis G. Riera

Ph.D. 2022

Joined Fall 2017Now: CSIRO's Data61

Ph.D., Mechanical Engineering, Iowa State University, 2022
M.S., Mechanical Engineering, Iowa State University, 1997
B.S., Mechanical Engineering, Iowa State University, 1995

About

Luis joined Dr. Sarkar's lab in August 2017. His research interests included deep learning, machine learning, visualization, and self-driving vehicles, including cars, trucks, and tractors. Before joining the lab, Luis worked mainly in project management and business development. His hobbies are go-kart racing, baking, mountain biking, and computers.

He graduated from the SCS Lab in November 2022 and is currently working at CSIRO's Data61.

Research interests: Deep learning, machine learning, visualization, self-driving vehicles

Publications with the lab (4)

Leveraging soil mapping and machine learning to improve spatial adjustments in plant breeding trials — Crop Science (2024)
Deep Multiview Image Fusion for Soybean Yield Estimation in Breeding Applications — Plant Phenomics (2021)

Show all 4

Detecting and tracking unsafe lane departure events for predicting driver safety in challenging naturalistic driving data — 2020 IEEE Intelligent Vehicles Symposium (IV) (2020)
Driver Behavior Analysis Using Lane Departure Detection Under Challenging Conditions — arXiv preprint arXiv:1906.00093 (2019)

lgriera (@) iastate.eduGoogle Scholar

Sin Yong Tan (Evan)

Ph.D. 2022

Joined Fall 2017Now: AI Scientist, Musco Sports Lighting, LLC

Ph.D., Mechanical Engineering, Iowa State University, 2022
B.S., Mechanical Engineering, Iowa State University, 2017

About

Sin Yong joined the lab in Fall 2017. He was involved in multiple projects, including the Autonomous Rover project and the Robot and Cop project, and gained hands-on experience with machine learning applications.

He graduated from the SCS Lab in December 2022 and is currently an AI Scientist at Musco Sports Lighting, LLC.

Research interests: Machine learning, deep learning, reinforcement learning, multimodal data, computer vision

Project: Autonomous Rover; Robot and Cop

Publications with the lab (19)

Few-shot deep learning for AFM force curve characterization of single-molecule interactions — Patterns (2023)
Active shooter detection and robust tracking utilizing supplemental synthetic data — arXiv preprint arXiv:2309.03381 (2023)

Show all 19

Multimodal sensor fusion framework for residential building occupancy detection — Energy and buildings (2022)
MDPGT: momentum-based decentralized policy gradient tracking — Proceedings of the AAAI conference on artificial intelligence (2022)
Whisper: wireless home identification and sensing platform for energy reduction — Journal of Sensor and Actuator Networks (2021)
A high-fidelity residential building occupancy detection dataset — Scientific Data (2021)
Decentralized Deep Learning Using Momentum-Accelerated Consensus — Preprint (2021)
Battery-free camera occupancy detection system — Proceedings of the 5th international workshop on embedded and mobile deep … (2021)
Cross-gradient aggregation for decentralized learning from non-iid data — International conference on machine learning (2021)
Spatiotemporal attention for multivariate time series prediction and interpretation — ICASSP 2021-2021 IEEE international conference on acoustics, speech and … (2021)
Interpretable Deep Attention Model for Multivariate Time Series Prediction in Building Energy Systems — Lecture notes in computer science (2020)
Interpretable Deep Learning for Monitoring Combustion Instability — IFAC-PapersOnLine (2020)
Granger causality based hierarchical time series clustering for state estimation — IFAC-PapersOnLine (2020)
On higher-order moments in adam — Beyond First Order Methods in Machine Learning Workshop, NeurIPS 2019 (2019)
An explainable framework using deep attention models for sequential data in combustion systems — NeurIPS 2019 workshop on machine learning and the physical sciences. NeurIPS (2019)
For publication in 2019 acc a flexible framework for building occupancy detection using spatiotemporal pattern networks — 2019 American Control Conference (ACC) (2019)
Learning State Switching for Improved Exploration in Multi-sensor Environments — (2019)
Learning State Switching for Multi-sensor Integration — (2019)
Temporal attention and stacked LSTMs for multivariate time series prediction — (2018)

tsyong98 (@) iastate.eduGoogle Scholar

Fateme Fotouhi Ardakani

Ph.D. 2023

Joined Fall 2019Now: Computer Vision Research Scientist, Canon

Ph.D., Mechanical Engineering, Iowa State University, 2023
M.S., Mechanical Engineering, Shiraz University, 2018
B.E., Mechanical Engineering, Shiraz University, 2015

About

Fateme joined the lab in Fall 2019. Her M.S. research was in control and vibration. Her main research interests included machine learning, deep learning, biomechanics, nonlinear control, robotics, mechatronics, and optimization. She is also interested in playing piano, reading, and mountain climbing.

She graduated from the SCS Lab in May 2023 and is currently a Computer Vision Research Scientist at Canon.

Research interests: Machine learning, deep learning, biomechanics, nonlinear control, robotics, mechatronics, optimization

Publications with the lab (10)

Persistent monitoring of insect-pests on sticky traps through hierarchical transfer learning and slicing-aided hyper inference — Frontiers in Plant Science (2024)
Dominating Set Model Aggregation for communication-efficient decentralized deep learning — Neural Networks (2024)

Show all 10

Smart connected farms and networked farmers to improve crop production, sustainability and profitability — Frontiers in Agronomy 6 (2024)
Cyber-agricultural systems for crop breeding and sustainable production — Trends in Plant Science 29 (2) (2024)
Smart Connected Farms and Networked Farmers to Tackle Climate Challenges Impacting Agricultural Production — arXiv (2023)
A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment — Frontiers in Robotics and AI (2022)
Deep learning-based phenotyping for genome wide association studies of sudden death syndrome in soybean — Frontiers in plant science (2022)
NAPPN Annual Conference Abstract: Genome wide association study of sudden death syndrome in soybean using deep learning-based phenotyping — Preprint (2022)
How useful is active learning for image‐based plant phenotyping? — The Plant Phenome Journal (2021)
Distributed deep learning for persistent monitoring of agricultural fields — NeurIPS 2021 AI for science workshop (2021)

fotouhif (@) iastate.eduGoogle Scholar

Jesse Lane

Ph.D. 2023

Joined Fall 2020Now: Principal Research Engineer, Collins Aerospace

Ph.D., Human Computer Interaction, Iowa State University, 2023
B.S., Computer Science, Iowa State University, 2005
B.S., Mathematics, Iowa State University, 2005

About

Jesse joined the Self-aware Complex Systems Lab in Fall 2020. His research interests lay at the intersection of causal inference, reinforcement learning, and deep learning. While in the lab, he was a Research Engineer at Collins Aerospace focusing on automatic target recognition and machine learning at the tactical edge. His hobbies are playing guitar and sailing.

He graduated from the SCS Lab in December 2023 and is now a Principal Research Engineer at Collins Aerospace, working across AI/ML, extended reality (XR), and operations engineering.

Research interests: Causal inference, reinforcement learning, deep learning

jalane (@) iastate.eduLinkedIn Homepage

Jiale Feng

Ph.D. 2024, Computer Science

Joined Summer 2021

Ph.D., Computer Science, Iowa State University, 2024
B.S., Automation, University of Science and Technology of China, 2014
B.S., Business Administration, University of Science and Technology of China, 2014

About

Jiale was a Ph.D. student in Computer Science and joined the Self-aware Complex Systems Laboratory in Summer 2021. Before that, he worked for five years in the ARLab at ISU's Virtual Reality Applications Center, mainly on individual projects funded by Collins Aerospace, and he interned at Collins Aerospace in the summers of 2017 and 2018. His research interests included deep learning, computer vision, and computer graphics. In his spare time, he keeps a consistent workout routine and enjoys PC games and movies.

Research interests: Deep learning, computer vision, computer graphics

Publications with the lab (3)

Robust soybean seed yield estimation using high-throughput ground robot videos — Frontiers in Plant Science (2025)
3D reconstruction of plants using probabilistic voxel carving — Computers and Electronics in Agriculture (2023)

Show all 3

Active shooter detection and robust tracking utilizing supplemental synthetic data — arXiv preprint arXiv:2309.03381 (2023)

colour (@) iastate.eduGoogle Scholar

Ashutosh Kumar Nirala

Ph.D. 2025

Now: Meta

Ph.D., Computer Science, Iowa State University, 2025
M.Tech., Computer Science, Indian Institute of Technology Bombay, India, 2013
B.S., Electronics and Telecommunication, Army Institute of Technology, Pune, India, 2007

About

Ashutosh was a Ph.D. student in the Department of Computer Science at Iowa State University, co-advised by Dr. Soumik Sarkar and Dr. Jin Tian. His research focused on adversarial robustness: developing methods that make deep learning models empirically robust while also providing avenues for their theoretical certification. His dissertation was titled "Toward Reliable AI: Practical and Certified Defenses for Adversarially Robust Vision Systems."

He graduated from the SCS Lab in December 2025 and is currently working at Meta.

Research interests: Adversarial robustness, certified defenses, robust vision systems

Publications with the lab (2)

TabQL: In-Context Q-Learning with Tabular Foundation Models — arXiv (2026)
Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing — 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) (2024)

aknirala (@) iastate.eduHomepage Google Scholar GitHub

Ethan Herron

Ph.D. 2026, Mechanical Engineering

Joined Summer 2020

Ph.D., Mechanical Engineering, Iowa State University, 2026
B.S., Mathematics, Iowa State University, 2020

About

Ethan was a Ph.D. student in Mechanical Engineering and joined the Self-aware Complex Systems Laboratory in Summer 2020, after receiving his B.S. in Mathematics from Iowa State University in Spring 2020. His research interests were machine learning, deep learning, and optimization, and he worked on applying deep learning methods to topology optimization. His other activities include high-powered rocketry, cooking, and various outdoor activities.

Research interests: Machine learning, deep learning, optimization

Publications with the lab (12)

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)

Show all 12

STITCH: Surface reconstrucTion using Implicit neural representations with Topology Constraints and persistent Homology — arXiv preprint arXiv:2412.18696 (2024)
Geometry matters: benchmarking scientific ml approaches for flow prediction around complex geometries — arXiv preprint arXiv:2501.01453 (2024)
Neural pde solvers for irregular domains — Computer-Aided Design (2024)
Latent diffusion models for structural component design — Computer-Aided Design (2024)
3d reconstruction of protein structures from multi-view afm images using neural radiance fields (nerfs) — Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern … (2024)
Deep learning-based 3D multigrid topology optimization of manufacturable designs — Engineering Applications of Artificial Intelligence (2023)
Generative design of material microstructures for organic solar cells using diffusion models — AI for Accelerated Materials Design NeurIPS 2022 Workshop (2022)
Algorithmically-consistent deep learning frameworks for structural topology optimization — Engineering Applications of Artificial Intelligence (2021)
Multigrid Distributed Deep CNNs for Structural Topology Optimization — AAAI 2022 Workshop on AI for Design and Manufacturing (ADAM) (2021)
Cross-gradient aggregation for decentralized learning from non-iid data — International conference on machine learning (2021)

edherron (@) iastate.eduGoogle Scholar

Muhammad Arbab Arshad

Ph.D. 2026

Joined Spring 2022Now: Software Engineer (AI), Waymo

Ph.D., Computer Science, Iowa State University, 2026
M.S., Computer Engineering, American University of Sharjah, 2021
B.S., Computer Science, Lahore University of Management Sciences, 2019

About

Arbab was a Ph.D. student in Computer Science at Iowa State University and a research assistant at the AI Institute for Resilient Agriculture (AIIRA). After joining Dr. Soumik Sarkar's lab in Spring 2022, his research centered on 3D reconstruction using neural radiance fields (NeRFs), with applications to soybean plants. He also explored the intersections of machine learning, computer vision, and generative AI, including large language models and MLOps.

He is currently a Software Engineer (AI) at Waymo.

Research interests: 3D reconstruction, neural radiance fields, computer vision, generative AI, large language models, MLOps

Publications with the lab (7)

SAGE: Scalable Agentic Grounded Evaluation for Crop Disease Diagnosis — CVPR 2026 Workshop on Emerging Directions in Data for Multimodal Foundation Models (DataMFM) (2026)
WeedNet: a foundation model-based global-to-local AI approach for weed species identification and classification — Nature Communications (2026)

Show all 7

Use of artificial intelligence in soybean breeding and production — Advances in Agronomy 190 (2025)
Leveraging vision language models for specialized agricultural tasks — 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV … (2025)
The impact of market orientation and brand storytelling on Shark Tank evaluations – a B2B and large language modeling perspective — Journal of Business and Industrial Marketing (2024)
Assisted few-shot learning for vision-language models in agricultural stress phenotype identification — Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning (2024)
Evaluating neural radiance fields for 3D plant geometry reconstruction in field conditions — Plant Phenomics (2024)

arbab (@) iastate.eduHomepage GitHub Faculty page

Masters Alumni

Sanjeda Akter

M.S. 2026

Joined Summer 2025Now: Ph.D. student

M.S., Computer Science, Iowa State University, 2026
B.S., Computer Science and Engineering, BRAC University, 2023

About

Sanjeda joined the lab in Summer 2025 as a master's student researcher in the Department of Computer Science at Iowa State University, where she focused on large language models and reinforcement learning. She completed her M.S. in 2026 and is now pursuing a Ph.D.

Research interests: Large language models, reinforcement learning

Google Scholar Faculty page GitHub

Independent Study Alumni

Minhao Wang

Independent Study Alumnus, Mechanical Engineering

Department of Mechanical Engineering, Iowa State University

About

Minhao Wang completed an independent study with the lab through the Department of Mechanical Engineering at Iowa State University, working on deep learning for image processing.

Research interests: Deep learning, image processing

Project: Deep Learning for Image Processing

Timothy Wilkie

Independent Study Alumnus, Mathematics

Department of Mathematics, Iowa State University

About

Timothy Wilkie completed an independent study with the lab through the Department of Mathematics at Iowa State University, working on distributed optimization.

Research interests: Distributed optimization

Project: Distributed Optimization

Publications with the lab (1)

Hierarchical Optimization for Building Energy Systems — (2018)

Seyed Vahid Mirnezami

Independent Study Alumnus, Mechanical Engineering

Department of Mechanical Engineering, Iowa State University

About

Seyed Vahid Mirnezami completed an independent study with the lab through the Department of Mechanical Engineering at Iowa State University, applying image processing and machine learning to the analysis of plant image data.

Research interests: Image processing, machine learning, plant image analysis

Project: Image Processing and Machine Learning for Analyzing Plant Image Data

Publications with the lab (4)

How useful is active learning for image‐based plant phenotyping? — The Plant Phenome Journal (2021)
High-throughput phenotyping in soybean — High-throughput crop phenotyping (2021)

Show all 4

Automated trichome counting in soybean using advanced image‐processing techniques — Applications in plant sciences (2020)
Computer vision and machine learning enabled soybean root phenotyping pipeline — Plant methods (2020)

Google Scholar

Undergraduate Alumni

Bukhari Mohamed

High School RA, CBiRC Young Engineers and Scientists Program

Roosevelt High School

About

Bukhari Mohamed, a student at Roosevelt High School, was a high school research assistant in the lab through the CBiRC Young Engineers and Scientists (YES) Program, working on image processing for predictive plant phenotyping.

Project: Image Processing for Predictive Plant Phenotyping

Jeffrey Heylmun

B.S. 2015, Mechanical Engineering · Former Undergraduate RA

B.S., Mechanical Engineering, Iowa State University, 2015

About

Jeffrey Heylmun earned his B.S. in Mechanical Engineering from Iowa State University in 2015. As an undergraduate research assistant in the lab, he worked on control-oriented modeling of building zone temperatures.

Project: Control-Oriented Modeling for Building Zone Temperatures

Publications with the lab (1)

Comparative evaluation of control-oriented zone temperature prediction modeling strategies in buildings — Dynamic Systems and Control Conference 57250, V002T34A009 (2015)

Adrian Kang Wei Chan

B.S. 2015, Mechanical Engineering · Former Undergraduate RA

B.S., Mechanical Engineering, Iowa State University, 2015

About

Adrian Kang Wei Chan earned his B.S. in Mechanical Engineering from Iowa State University in 2015. As an undergraduate research assistant in the lab, he worked on information topology control in networked systems.

Project: Information Topology Control in Networked Systems

Adam Kohl

B.S. 2015, Mechanical Engineering · Former Undergraduate RA

B.S., Mechanical Engineering, Iowa State University, 2015

About

Adam Kohl earned his B.S. in Mechanical Engineering from Iowa State University in 2015. As an undergraduate research assistant in the lab, he worked on control-oriented modeling of building zone temperatures using VOLTTRON.

Project: Control-Oriented Modeling for Building Zone Temperatures Using VOLTTRON

Publications with the lab (4)

Supervisory control and distributed optimization of building energy systems — Journal of Dynamic Systems, Measurement, and Control (2020)
Scalable supervisory control of building energy systems using generalized gossip — 2016 American Control Conference (ACC) (2016)

Show all 4

A volttron based implementation of supervisory control using generalized gossip for building energy systems — (2016)
Comparative evaluation of control-oriented zone temperature prediction modeling strategies in buildings — Dynamic Systems and Control Conference 57250, V002T34A009 (2015)

Xuehan Liu

B.S. 2016, Statistics and Mathematics · Former Undergraduate RA

B.S., Statistics and Mathematics, Iowa State University, 2016

About

Xuehan Liu earned a B.S. in Statistics and Mathematics from Iowa State University in 2016. As an undergraduate research assistant in the lab, Xuehan worked on mathematical modeling of amyotrophic lateral sclerosis (ALS).

Project: Mathematical Modeling of Amyotrophic Lateral Sclerosis (ALS)

Abdulrahman Alnagar

Former Undergraduate RA and REU Student, Electrical Engineering

Department of Electrical Engineering

About

Abdulrahman Alnagar was an undergraduate research assistant and REU student in the lab from the Department of Electrical Engineering, working on anomaly detection for smart buildings.

Project: Anomaly Detection for Smart Buildings

Haley Primrose

High School RA, Young Engineers and Scientists (YES) Program

Nevada High School

About

Haley Primrose, a student at Nevada High School, joined the lab for the summer through the Young Engineers and Scientists (YES) Program. She worked on a manufacturing project aimed at having the Sawyer robot reach into a 3D-printer station and autonomously retrieve printed parts. At the time, she planned to study computer engineering at Iowa State after graduating from high school.

Project: Autonomous Retrieval of 3D-Printed Parts with the Sawyer Robot

Matthew Hopkins

High School RA, Young Engineers and Scientists (YES) Program

Abraham Lincoln High School

About

Matthew Hopkins, a student at Abraham Lincoln High School, spent six weeks in the lab over the summer through the Young Engineers and Scientists (YES) Program to explore his interest in engineering. He worked on the TurtleBot, programming and testing RGB color values for automated color detection with the robot's vision system while it moved. Interested in robotics, he hoped to join a program at Iowa State that would let him build, program, and test robotic systems.

Research interests: Robotics

Project: Automated Color Detection with the TurtleBot Vision System

Aaron Havens

B.S. 2017, Mechanical Engineering

Now: Postdoctoral Researcher, Meta Fundamental AI Research (FAIR)

Ph.D., Electrical and Computer Engineering, University of Illinois Urbana-Champaign
B.S., Mechanical Engineering, Iowa State University, 2017

About

Aaron Havens earned his B.S. in Mechanical Engineering from Iowa State University in 2017. As an undergraduate research assistant in the lab, he worked on online robust policy learning in the presence of unknown adversaries, which led to a NeurIPS 2018 paper with Zhanhong Jiang and Soumik Sarkar.

He went on to earn a Ph.D. in Electrical and Computer Engineering at the University of Illinois Urbana-Champaign under Prof. Bin Hu, working at the intersection of robust control theory and machine learning. He is now a postdoctoral researcher at Meta Fundamental AI Research (FAIR), working on scalable methods for generative modeling and reward-based fine-tuning, with applications to modeling physical processes in science and engineering.

Research interests: Generative modeling, reward-based fine-tuning, robust control, machine learning

Project: Online Robust Policy Learning in the Presence of Unknown Adversaries

Publications with the lab (2)

Learning to cope with adversarial attacks — arXiv preprint arXiv:1906.12061 (2019)
Online robust policy learning in the presence of unknown adversaries — Advances in neural information processing systems (2018)

Homepage Google Scholar GitHub

Balaji S Sarath Pokuri

Former Researcher, Mechanical Engineering

Department of Mechanical Engineering, Iowa State University

About

Balaji S Sarath Pokuri worked with the lab from the Department of Mechanical Engineering at Iowa State University. His interests spanned phase-field modeling, high-performance computing (HPC), the finite element method (FEM), and machine learning, particularly deep learning.

Research interests: Phase-field modeling, high-performance computing (HPC), finite element method (FEM), machine learning, deep learning

Publications with the lab (10)

Multi-fidelity machine learning models for structure–property mapping of organic electronics — Computational Materials Science (2022)
Generative design of material microstructures for organic solar cells using diffusion models — AI for Accelerated Materials Design NeurIPS 2022 Workshop (2022)

Show all 10

Fast inverse design of microstructures via generative invariance networks — Nature Computational Science (2021)
Inverse design of microstructures via generative networks for organic solar cells — AAAI 2022 Workshop on AI for Design and Manufacturing (ADAM) (2021)
InvNet: encoding geometric and statistical invariances in deep generative models — Proceedings of the AAAI Conference on Artificial Intelligence (2020)
Encoding Invariances in Deep Generative Models — arXiv preprint arXiv:1906.01626 (2019)
Generative models for solving nonlinear partial differential equations — Proc. of NeurIPS Workshop on ML for Physics (2019)
Binary 2d morphologies of polymer phase separation: Dataset and python toolbox — (2019)
Interpretable deep learning for guided microstructure-property explorations in photovoltaics — npj Computational Materials (2019)
Physics-aware deep generative models for creating synthetic microstructures — arXiv preprint arXiv:1811.09669 (2018)

Paige K Boor

Former Undergraduate Honors Student, Mechanical Engineering

Joined Spring 2017

Department of Mechanical Engineering, Iowa State University

About

Paige K Boor was an undergraduate honors student in the Department of Mechanical Engineering at Iowa State University. She joined the lab in Spring 2017 to learn more about machine learning.

Research interests: Machine learning

Publications with the lab (4)

3D convolutional selective autoencoder for instability detection in combustion systems — Energy and AI (2021)
Characterizing Combustion Instability Using Deep Convolutional Neural Network — (2018)

Show all 4

Mode decomposition and convolutional neural network analysis of thermoacoustic instabilities in a rijke tube — (2018)
High speed video-based health monitoring using 3D deep learning — Dynamic Data-Driven Application Systems (DDDAS) (2017)

Genyi Huang

Former Undergraduate Researcher, Statistics

Department of Statistics, Iowa State University

About

Genyi Huang was an undergraduate researcher from the Department of Statistics at Iowa State University. In the lab, Genyi worked on LSTM and attention models for time-series prediction, contributing to the 2018 paper "Temporal Attention and Stacked LSTMs for Multivariate Time Series Prediction."

Research interests: Deep learning, time-series prediction, statistics

Project: LSTM and Attention Models for Time-Series Prediction Problems

Publications with the lab (2)

FUSE: First-Order and Second-Order Unified Synthesis in Stochastic Optimization — 2025 IEEE Conference on Artificial Intelligence (CAI) (2025)
Temporal attention and stacked LSTMs for multivariate time series prediction — (2018)

Google Scholar

Mason Drees

Former Undergraduate RA, Mechanical Engineering

Joined Fall 2020

Department of Mechanical Engineering, Iowa State University

About

Mason Drees was an undergraduate research assistant majoring in Mechanical Engineering with a minor in Computer Science at Iowa State University. He joined the lab in Fall 2020, and his research interests included reinforcement learning applications in robotics.

Research interests: Reinforcement learning for robotics

Aakanksha

Former Undergraduate Researcher, Amity University

Joined Summer 2019

Amity University, Noida

About

Aakanksha was a final-year undergraduate at Amity University, Noida, pursuing a Bachelor of Technology (B.Tech.) in Computer Science. She joined the lab in Summer 2019 and worked on problems involving reinforcement learning. Her research interests included machine learning and deep learning for object detection and computer vision.

Research interests: Machine learning, reinforcement learning, deep learning for object detection, computer vision

Briton R Bauerly

Former Undergraduate Researcher, Mechanical Engineering

Joined Summer 2019

Department of Mechanical Engineering, Iowa State University

About

Briton R Bauerly was an undergraduate Mechanical Engineering student at Iowa State University who joined the lab in Summer 2019. His research interests included deep learning for robotics applications, and his other interests include 3D printing, tennis, and film.

Research interests: Deep learning for robotics

Yingying Huang

Former Undergraduate Honors Student, Mechanical Engineering

Joined Fall 2021

Department of Mechanical Engineering, Iowa State University

About

Yingying Huang joined the lab in Fall 2021 and worked on robotics applications as an undergraduate honors student in the Department of Mechanical Engineering at Iowa State University.

Research interests: Robotics

David Leguizamo

Former Undergraduate RA, Mechanical Engineering

Joined Fall 2021

Department of Mechanical Engineering, Iowa State University

About

David Leguizamo joined the lab in Fall 2021 as an undergraduate research assistant in the Department of Mechanical Engineering at Iowa State University, working on robotics applications. His work included the 2022 paper "Deep Reinforcement Learning for Robotic Control with Multi-Fidelity Models" with Soumik Sarkar.

Research interests: Deep reinforcement learning, robotic control

Publications with the lab (1)

Deep Reinforcement Learning for Robotic Control with Multi-Fidelity Models — IFAC-PapersOnLine (2022)

Google Scholar