MAGI Lab

Assistant Professor · University of Nevada, Reno

Ankita Shukla

I develop reliable and interpretable AI methods for visual, multimodal, scientific, and socially meaningful data, with applications in medical AI, geometric intelligence, and AI for Good.

PI, MAGI Lab
About Me UNR Scholar Email

MAGI Lab

MAGI Lab develops machine learning and deep learning methods for visual, multimodal, and time series data, with an emphasis on geometric structure, reliability, and interpretability.

Our work connects geometric intelligence with applications in medical AI, scientific discovery, and AI for Good.

Visit the MAGI Lab page

News

More
  • 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.

Join Information

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.

Lab Updates

Recent publications, public articles, and lab milestones.

  • 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.

Ankita Shukla

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

Office
WPEB 435
UNR Scholar Twitter

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

2025

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

2023

2022

2021

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

2019

2018 and Earlier

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
Email Ankita

Contact

MAGI Lab at UNR.

Department

Computer Science and Engineering
University of Nevada, Reno
William N. Pennington Engineering Building
Reno, NV 89557

UNR profile Personal site