Publications

FAccT 2026

"Where is this coming from?" Uncovering Trustworthiness Ideals in AI-powered Peripartum Information Seeking

Vaibhav Balloli, Julia Erickson, Xinyi Li, Erin van Liemt, Alex Peahl, Elizabeth Bondi-Kelly

Focus groups with patients and clinicians surface the role of AI-enabled information provision in peripartum care, and the trustworthiness and governance expectations different stakeholders hold.

Project

@inproceedings{balloli2026trustworthiness,
  title     = {''Where is this coming from?'' Uncovering Trustworthiness Ideals in {AI}-powered Peripartum Information Seeking},
  author    = {Balloli, Vaibhav and Erickson, Julia and Li, Xinyi and van Liemt, Erin and Peahl, Alex and Bondi-Kelly, Elizabeth},
  booktitle = {ACM Conference on Fairness, Accountability, and Transparency (FAccT)},
  year      = {2026}
}

ML4RS @ ICLR 2026 Workshop

Spotlight Oral (~10%)Best Paper Award

FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping

Jowaria Khan, Alexa Friedman, Sydney Evans, Rachel Klein, Runzi Wang, Katherine E. Manz, Kaley Beins, David Q. Andrews, Elizabeth Bondi-Kelly

A hydrology-informed, noise-aware learning approach for mapping PFAS “forever chemical” contamination across geographies from sparse, noisy measurements.

arXiv

@inproceedings{khan2026focus,
  title     = {{FOCUS} on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial {PFAS} Mapping},
  author    = {Khan, Jowaria and Friedman, Alexa and Evans, Sydney and Klein, Rachel and Wang, Runzi and Manz, Katherine E. and Beins, Kaley and Andrews, David Q. and Bondi-Kelly, Elizabeth},
  booktitle = {ICLR Machine Learning for Remote Sensing (ML4RS) Workshop},
  year      = {2026}
}

KDD 2026

RELIANCE: Curating and Evaluating Reproductive Health Information on Social Media

Vaibhav Balloli, Laura Peyton Ellis, Vishala Mishra, Alice M Chi, Alex Peahl, Elizabeth Bondi-Kelly

Multi-modal agents curate reproductive-health information from social media, and we work with clinicians to evaluate the accuracy of the content — and how well LLMs assess it for accuracy and harms.

Project

@inproceedings{balloli2026reliance,
  title     = {{RELIANCE}: Curating and Evaluating Reproductive Health Information on Social Media},
  author    = {Balloli, Vaibhav and Ellis, Laura Peyton and Mishra, Vishala and Chi, Alice M and Peahl, Alex and Bondi-Kelly, Elizabeth},
  booktitle = {ACM Knowledge Discovery and Data Mining (KDD)},
  year      = {2026}
}

Interactive Health 2026 Demos & Exhibitions

PATHFinder Agent for Tailored Prenatal Care

Vaibhav Balloli, Carissa Samuel, Samia Abdelnabi, Alex Peahl, Elizabeth Bondi-Kelly

Interactive LLM agents talk with pregnant people to provide personalized prenatal-care information, plans, and resources — and assist clinicians.

Project

@inproceedings{balloli2026pathfinder,
  title     = {{PATHFinder} Agent for Tailored Prenatal Care},
  author    = {Balloli, Vaibhav and Samuel, Carissa and Abdelnabi, Samia and Peahl, Alex and Bondi-Kelly, Elizabeth},
  booktitle = {ACM Interactive Health, Demos and Exhibitions},
  year      = {2026}
}

Preprint 2025

Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery

Jowaria Khan, Anindya Sarkar, Yevgeniy Vorobeychik, Elizabeth Bondi-Kelly

Relevance-guided online meta-learning with latent concepts that adapts on the fly to discover rare geospatial phenomena efficiently.

arXiv

@article{khan2025adapting,
  title  = {Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery},
  author = {Khan, Jowaria and Sarkar, Anindya and Vorobeychik, Yevgeniy and Bondi-Kelly, Elizabeth},
  year   = {2025}
}

AI Magazine 2025

Human at the Center: A Framework for Human-Driven AI Development

Danniell Hu, Diana Acosta Navas, Susanne Gaube, Hussein Mozannar, Matthew E. Taylor, Krishnamurthy Dvijotham, Elizabeth Bondi-Kelly

A framework for centering people throughout the AI development lifecycle — from problem formulation to deployment — so systems reflect the needs of the communities they serve.

@article{hu2025humancenter,
  title   = {Human at the Center: A Framework for Human-Driven AI Development},
  author  = {Hu, Danniell and Acosta Navas, Diana and Gaube, Susanne and Mozannar, Hussein and Taylor, Matthew E. and Dvijotham, Krishnamurthy and Bondi-Kelly, Elizabeth},
  journal = {AI Magazine},
  year    = {2025}
}

AIES 2025 AAAI/ACM Conf. on AI, Ethics, and Society

RelAItionship Building: Analyzing Recruitment Strategies for Participatory AI

Eugene Kim, Vaibhav Balloli, Berelian Karimian, Elizabeth Bondi-Kelly, Ben Fish

An analysis of how participatory-AI projects recruit community participants, and what recruitment strategies mean for whose voices shape the resulting systems.

arXiv

@inproceedings{kim2025relaitionship,
  title     = {RelAItionship Building: Analyzing Recruitment Strategies for Participatory AI},
  author    = {Kim, Eugene and Balloli, Vaibhav and Karimian, Berelian and Bondi-Kelly, Elizabeth and Fish, Ben},
  booktitle = {AAAI/ACM Conference on AI, Ethics, and Society (AIES)},
  year      = {2025}
}

IJCAI 2024 Human-Centered AI track

CV4Animals @ CVPR 2024 Workshop

<5% accept

Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval

Vaibhav Balloli, Sara Beery, Elizabeth Bondi-Kelly

CHAIR adapts Concept Bottleneck Models so experts can intervene on intermediate concepts during image retrieval — useful for wildlife re-identification platforms like ElephantBook — letting domain experts spend effort where it is most valuable.

Project Code

@inproceedings{balloli2024chair,
  title     = {Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval},
  author    = {Balloli, Vaibhav and Beery, Sara and Bondi-Kelly, Elizabeth},
  booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
  year      = {2024}
}

CCAI @ NeurIPS 2024 Tackling Climate Change with ML Workshop

AI-Driven Predictive Modeling of PFAS Contamination in Aquatic Ecosystems: Exploring a Geospatial Approach

Jowaria Khan, David Andrews, Kaley Beins, Alexa Friedman, Sydney Evans, Elizabeth Bondi-Kelly

A geospatial machine-learning approach to predicting PFAS contamination in aquatic ecosystems, supporting environmental-health monitoring.

@inproceedings{khan2024pfas,
  title     = {AI-Driven Predictive Modeling of {PFAS} Contamination in Aquatic Ecosystems: Exploring a Geospatial Approach},
  author    = {Khan, Jowaria and Andrews, David and Beins, Kaley and Friedman, Alexa and Evans, Sydney and Bondi-Kelly, Elizabeth},
  booktitle = {Tackling Climate Change with Machine Learning Workshop, NeurIPS},
  year      = {2024}
}

All publications

"Where is this coming from?" Uncovering Trustworthiness Ideals in AI-powered Peripartum Information Seeking

FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping

RELIANCE: Curating and Evaluating Reproductive Health Information on Social Media

PATHFinder Agent for Tailored Prenatal Care

Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery

Human at the Center: A Framework for Human-Driven AI Development

RelAItionship Building: Analyzing Recruitment Strategies for Participatory AI

Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval

AI-Driven Predictive Modeling of PFAS Contamination in Aquatic Ecosystems: Exploring a Geospatial Approach