MAGI Lab
- Machine learning and deep learning for visual, multimodal, and time series data.
- Geometry-aware, reliable, and interpretable AI methods.
- Applications in medical AI, scientific discovery, and AI for Good.
News
More- Preprint ConceptM3oE arXiv preprint released for interpretable computational pathology.
- Teaching ENG 481/681 Introduction to AI for Engineering will be offered in Fall 2026.
- Paper Paper titled "Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images" accepted to ICHI.
- Preprint PathMoE arXiv preprint released for pediatric brain tumor classification with interpretable multimodal experts.
- Paper Paper titled "Hyperbolic Embeddings Improve Narrative Quality in Retrieval-Augmented Generation Models" appeared at WACV Workshops, LENS.
- Paper IJCV paper on polynomial implicit neural frameworks for shape awareness in generative models published.
Methods for AI and Geometric Intelligence
(ma·jai)
MAGI Lab
MAGI Lab develops reliable, interpretable, and geometry-aware AI methods for scientific and socially meaningful problems.
Lab Mission
Building AI methods that respect structure and work in real-world settings.
Methods
We develop machine learning and deep learning approaches for visual, multimodal, and time series data.
Geometric Intelligence
We study geometry-driven learning, topology, shape awareness, and structure-aware representations.
AI for Good
We apply AI to medical AI, scientific discovery, wildlife conservation, and other socially meaningful domains.
Current Focus
Research directions currently shaping the group.
Medical AI
Clinically informed models for health and pathology data.
LLMs and Multimodal AI
Language, vision-language, and multimodal reasoning systems.
Geometric Learning
Geometry, topology, and structure-aware representation learning.
AI for Good
AI methods for science, conservation, and human-centered impact.
Lab Culture
How we approach research, collaboration, and student growth.
Method-first research
We build careful AI methods, then test them on meaningful real-world problems where structure and reliability matter.
Interdisciplinary work
We collaborate across computer science, medicine, engineering, science, and socially impactful application areas.
Student growth
Students are encouraged to develop strong technical foundations, clear research taste, and confidence presenting their work.
Join MAGI Lab
We welcome motivated students interested in AI, geometry, multimodal learning, medical AI, and AI for Good.
News and Public Articles
Lab updates and media.
Public-facing articles, research announcements, paper acceptances, talks, and lab milestones.
Public Articles
Stories and announcements written for a broad audience.
April 1, 2026
Researchers to use robotics and AI to help sheep producers
Nevada Today article mentioning Ankita Shukla’s role in developing AI models that analyze sensor data for RoboHydra.
March 6, 2026
Computer Science & Engineering professors lead $1 million medical AI research project
Nevada Today article on UNR research with George Bebis and Ankita Shukla focused on reliable AI for breast cancer, medical text, and sleep disorders.
Lab Updates
Recent publications, public articles, and lab milestones.
- Preprint ConceptM3oE arXiv preprint released: "Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology."
- Teaching ENG 481/681 Introduction to AI for Engineering will be offered in Fall 2026.
- Paper Paper titled "Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images" accepted to ICHI 2026.
- Preprint PathMoE arXiv preprint released: "Interpretable Multimodal Interaction Experts for Pediatric Brain Tumor Classification."
- Paper Paper titled "Hyperbolic Embeddings Improve Narrative Quality in Retrieval-Augmented Generation Models" appeared at WACV Workshops, LENS 2026.
- Media Nevada Today featured UNR medical AI research on reliable models for breast cancer, medical text, and sleep disorders.
- Media Nevada Today covered robotics and AI research for sheep producers, including AI models for RoboHydra sensor data.
- IJCV paper "Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models" published.
- MMLoSo 2025 workshop and shared-task proceedings published in ACL Anthology.
- Paper titled "Orthogonality and graph divergence losses promote disentanglement in generative models" published in Frontiers in Computer Science.
- Paper titled "Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments" accepted at DLGC, CVPR.
- Paper titled "Polynomial Implicit Neural Representations For Large Diverse Datasets" accepted at CVPR.
- Paper titled "Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study" accepted at WACV.
- Paper titled "Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures" accepted.
- Presented work on "AI based tool for Beluga Whale Conservation and Monitoring" at Ocean Sciences Meeting.
Research
Research Areas
MAGI Lab develops AI methods that combine geometric structure, multimodal learning, and real-world impact.
01
Medical AI
Reliable AI systems for health applications, including medical imaging, clinical text, sleep disorders, and translation from models to real-world settings.
02
Large Language Models and Multimodal AI
Methods for language, vision-language, and multimodal reasoning systems, with attention to reliability and evaluation.
03
Geometric and Topological Learning
Geometry-driven deep learning, topological data analysis, shape awareness, and structure-aware representations.
04
AI for Good
AI methods for socially meaningful applications, including human health, scientific discovery, and wildlife conservation.
People
The MAGI Lab group.
Principal Investigator
Ankita Shukla
Bio
I am an Assistant Professor in the Computer Science and Engineering Department at University of Nevada Reno, USA. Before joining UNR, I was a Postdoctoral researcher in the Geometric Media Lab, working with Prof. Pavan Turaga at Arizona State University.
Research Interests
My research interests lie in deep learning and machine learning approaches for visual and time series data, topological data analysis, differential geometry, and geometry driven approaches for learning. From the applications point of view, I focus on AI for Science and AI for Good, specifically towards wildlife conservation and human health applications.
Education & Training
- 2021-2023: Postdoctoral Researcher, Geometric Media Lab, Arizona State University
- 2020: Ph.D., IIIT-Delhi
- Dissertation: "Exploring Geometric Constraints for Learning Representations for Visual Data"
- 2014: Master's degree, IIIT-Delhi
- Best Thesis Award for work on energy-efficient EEG acquisition and transmission for WBAN
Contact
- ankitas@unr.edu
- Office
- WPEB 435
Ph.D. Students
Current MAGI Lab members.
✨
Ph.D. Student
Mahmoud Fakhry
Ph.D. student in MAGI Lab. Research interests will be updated with current project focus.
✨
Ph.D. Student
Malak Bachri
Ph.D. student in MAGI Lab. Research interests will be updated with current project focus.
Master's Students
Current MAGI Lab members.
Master's Student
Jude Koeing
Master's student in MAGI Lab. Research interests will be updated with current project focus.
Master's Student
Richie White
Master's student in MAGI Lab. Research interests will be updated with current project focus.
✨
Master's Student
Carter Webb
Master's student in MAGI Lab. Research interests will be updated with current project focus.
Undergraduate Students
Future MAGI Lab members.
Undergraduate researchers, honors students, and project contributors will be listed here.
Alumni
Former lab members.
Former students, visitors, and collaborators will be listed here as the lab grows.
Publications
Publications.
Work across geometric learning, computer vision, robust representations, scientific AI, and conservation applications.
2026
2026
ConceptM3oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology
Xuan Wang, Zhongling Xu, Gopi Kannedhara, Joakim Nguyen, Jian Yu, Jinrui Fang, Abdurrahmaan Baghdadi, Tianlong Chen, Awais Naeem, Chandra Krishnan, Edward Castillo, Andrew H. Song, Ankita Shukla, Ying Ding, Nicholas Konz, Hairong Wang.
arXiv:2605.24399
2026
Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images
Joakim Nguyen, Jian Yu, Jinrui Fang, Nicholas Konz, Tianlong Chen, Sanjay Krishnan, Chandra Krishnan, Ying Ding, Hairong Wang, Ankita Shukla.
ICHI 2026; arXiv:2604.21060
2026
PathMoE: Interpretable Multimodal Interaction Experts for Pediatric Brain Tumor Classification
Jian Yu, Joakim Nguyen, Jinrui Fang, Awais Naeem, Zeyuan Cao, Sanjay Krishnan, Nicholas Konz, Tianlong Chen, Chandra Krishnan, Hairong Wang, Edward Castillo, Ying Ding, Ankita Shukla.
arXiv:2603.01547
2026
Hyperbolic Embeddings Improve Narrative Quality in Retrieval-Augmented Generation Models
Mayukh Debnath, Ankita Shukla.
WACV 2026 Workshops, LENS: Learning and Exploitation of Latent Space Geometries, pp. 1326-1333
2025
2025
Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
Gunner Stone, Youngsook Choi, Alireza Tavakkoli, Ankita Shukla.
arXiv:2509.17207
2025
Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models
Utkarsh Nath, Rajhans Singh, Ankita Shukla, Kuldeep Kulkarni, Pavan K. Turaga.
International Journal of Computer Vision, 133(5): 2967-2995
2025
Intra-class patch swap for self-distillation
Hongjun Choi, Eun Som Jeon, Ankita Shukla, Pavan K. Turaga.
Neurocomputing, 645: 130408
2025
Ground Reaction Force Estimation via Time-Aware Knowledge Distillation
Eun Som Jeon, Sinjini Mitra, Jisoo Lee, Omik M. Save, Ankita Shukla, Hyunglae Lee, Pavan K. Turaga.
IEEE Internet of Things Journal, 12(16): 34406-34420
2025
MMLoSo 2025: Workshop and Shared Task Proceedings
Ankita Shukla, Sandeep Kumar, Amrit Singh Bedi, Tanmoy Chakraborty, Pooja Singh, Sandeep Chatterjee, Gullal S. Cheema.
1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact; Shared Task on Machine Translation into Tribal Languages
2024
2024
Topological persistence guided knowledge distillation for wearable sensor data
Eun Som Jeon, Hongjun Choi, Ankita Shukla, Yuan Wang, Hyunglae Lee, Matthew P. Buman, Pavan K. Turaga.
Engineering Applications of Artificial Intelligence, 130: 107719
2024
Robustness of topological persistence in knowledge distillation for wearable sensor data
Eun Som Jeon, Hongjun Choi, Ankita Shukla, Yuan Wang, Matthew P. Buman, Hyunglae Lee, Pavan K. Turaga.
EPJ Data Science, 13(1): 77
2024
Orthogonality and graph divergence losses promote disentanglement in generative models
Ankita Shukla, Rishi Dadhich, Rajhans Singh, Anirudh Rayas, Pouria Saidi, Gautam Dasarathy, Visar Berisha, Pavan K. Turaga.
Frontiers in Computer Science, 6
2024
On the impact of pre-training datasets for matching dendritic identifiers using residual nets
Baaz Jhaj, Ankita Shukla, Pavan K. Turaga, Michael N. Kozicki.
AI-SIPM 2024
2023
2023
Leveraging angular distributions for improved knowledge distillation
Eun Som Jeon, Hongjun Choi, Ankita Shukla, Pavan K. Turaga.
Neurocomputing, 518: 466-481
2023
Constrained Adaptive Distillation Based on Topological Persistence for Wearable Sensor Data
Eun Som Jeon, Hongjun Choi, Ankita Shukla, Yuan Wang, Matthew P. Buman, Pavan K. Turaga.
IEEE Transactions on Instrumentation and Measurement, 72: 1-14
2023
Scene Graph Driven Text-Prompt Generation for Image Inpainting
Tripti Shukla, Paridhi Maheshwari, Rajhans Singh, Ankita Shukla, Kuldeep Kulkarni, Pavan K. Turaga.
CVPR Workshops 2023
2023
Polynomial Implicit Neural Representations For Large Diverse Datasets
Rajhans Singh, Ankita Shukla, Pavan Turaga.
CVPR 2023
2023
Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
Rajhans Singh, Ankita Shukla, Pavan Turaga.
DLGC, CVPR 2023
2023
Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study
Hongjun Choi, Eunsom Jeon, Ankita Shukla, Pavan Turaga.
WACV 2023
2022
2022
Learning Free Energy Pathways through Reinforcement Learning of Adaptive Steered Molecular Dynamics
Nicholas Ho, John Kevin Cava, John Vant, Ankita Shukla, Jake Miratsky, Pavan Turaga, Ross Maciejewski, Abhishek Singharoy.
MLSB, NeurIPS 2022
2022
The Gradient-Boosting Method for Tackling High Computing Demand in Underwater Acoustic Propagation Modeling
D. Lagrois, T. R. Bonnell, A. Shukla, C. Chion.
Journal of Marine Science and Engineering
2022
Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data
E. Jeon, A. Som, A. Shukla, K. Hasanaj, M. P. Buman, P. Turaga.
IEEE Internet of Things Journal
2022
Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures
V. M. Arujo, Ankita Shukla, C. Chion, S. Gambs, R. Michaud.
Sensors and Artificial Intelligence for Wildlife Conservation
2022
Deep Geometric Moment
R. Singh, A. Shukla, Pavan Turaga.
2021
2021
Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
Ankita Shukla, R. Anirudh, E. Kur, J. J. Thiagarajan, P. Bremer, B. K. Spears, T. Ma, Pavan Turaga.
Machine Learning for Physical Sciences, NeurIPS 2021
2021
Towards Conditional Generation of Minimal Action Potential Pathways for Molecular Dynamics
J. K. Cava, J. Vant, N. Ho, A. Shukla, Pavan Turaga, R. Maciejewski, A. Singharoy.
ELLIS Machine Learning for Molecule Discovery Workshop
2021
Cleaning Adversarial Perturbations with Image-Subspace Projections
Ankita Shukla, Pavan Turaga, Saket Anand.
3rd Workshop on Adversarial Learning Methods for Machine Learning and Data Mining, KDD 2021
2020
2020
GraCIAS: Grassmannian of Corrupted Images for Adversarial Security
A. Shukla, Pavan Turaga, Saket Anand.
2020
2019
2019
A Hybrid Approach for Tiger Re-Identification
Ankita Shukla, C. Anderson, G. S. Cheema, P. Guo, S. Onda, D. Anshumaan, S. Anand, R. Farrell.
CVWC, ICCV 2019
2019
PrOSe: Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning
Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand, Pavan Turaga.
BMVC 2019
2019
Primate Face Identification in the Wild
Ankita Shukla*, Gullal Singh Cheema*, Saket Anand, Qamar Qureshi, Yadvendradev Jhala.
PRICAI 2019 (*Equal Contribution)
2018 and Earlier
2018
Geometry of Deep Generative Models for Disentangled Representations
Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand, Pavan Turaga.
ICVGIP 2018
2018
Perturbation Robust Representations of Topological Persistence Diagrams
Anirudh Som, Kowshik Thopalli, K. N. Ramamurthy, V. Venkataraman, Ankita Shukla, Pavan Turaga.
ECCV 2018
2017
Metric Learning on Biological Sequence Embeddings
Dhananjay Kimothi, Ankita Shukla, Pravesh Biyani, Saket Anand, James M. Hogan.
SPAWC 2017
2017
Energy efficient EEG acquisition and reconstruction for a Wireless Body Area Network
Wazir Singh, Ankita Shukla, Sujay Deb, Angshul Majumdar.
Integration, the VLSI Journal
2016
Metric Learning based Automatic Segmentation of Patterned Species
Ankita Shukla, Saket Anand.
ICIP 2016
2015
Distance Metric Learning by Optimization on the Stiefel Manifold
Ankita Shukla, Saket Anand.
Differential Geometry in Computer Vision, BMVC 2015 (Best Student Paper)
Teaching
Courses at UNR.
Courses taught in artificial intelligence, large language models, and multimodal AI at the University of Nevada, Reno.
ENG 481/681
Introduction to AI for Engineering
Fall 2026
CS 482/682
Artificial Intelligence
Fall 2024, Fall 2025
CS 791
Recent Trends in Large Language Models
Fall 2024
CS 491/691
Large Language Models and Multimodal AI
Spring 2025
Join MAGI Lab
Prospective students and collaborators.
I am looking for highly self-motivated Ph.D., graduate, and undergraduate students with a strong commitment to research.
What to Send
- CV or resume
- Transcripts
- TOEFL/GRE scores, if applicable
- Brief research interests and relevant materials
Contact
MAGI Lab at UNR.
Ankita Shukla
Emailankitas@unr.edu
Phone(775) 682-5318
OfficeWPEB 435
Department
Computer Science and Engineering
University of Nevada, Reno
William N. Pennington Engineering Building
Reno, NV 89557