Curriculum Vitae

Education

• University of Michigan, Ann Arbor

  2023 – present

  Ph.D. Candidate, M.S. in Computer Science and Engineering

  Advised by Prof. Elizabeth Bondi-Kelly. Coursework in reinforcement learning theory, causality and ML, NLP, HCI, AI, and advanced data mining.

• BITS Pilani, Hyderabad Campus

  2016 – 2020

  B.E. in Electronics and Communication Engineering

Research experience

• Microsoft Research Redmond, AI Frontiers

  May – Aug 2025

  Research Intern

  Multi-turn reinforcement learning with large language model agents, and agent evaluation. Advised by Hussein Mozannar, Adam Fourney, Gagan Bansal, Saleema Amershi, and Eric Horvitz.

• Microsoft Research India

  Jun 2022 – Jun 2023

  Research Fellow

  Reinforcement learning and large language models on Project Vasudha and Project VeLLM. Advised by Dr. Akshay Nambi and Tanuja Ganu.

• Microsoft Research India

  Jun 2021 – Jun 2022

  Societal Impact through Cloud and AI Fellow

  Computer vision, bandits, and localisation for HAMS. Advised by Dr. Akshay Nambi, Tanuja Ganu, and Dr. Venkat Padmanabhan.

Publications

1. RELIANCE: Curating and Evaluating Reproductive Health Information on Social Media

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

   KDD 2026 · Datasets and Benchmarks Track

2. PATHFinder Agent for Tailored Prenatal Care

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

   Interactive Health 2026

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

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

   FAccT 2026

4. SEEK-CBM: Editable and Interpretable Retrieval for Elephant Re-Identification

   Antoine Salaün, Vaibhav Balloli, Timm Haucke, Elizabeth Bondi-Kelly, Sara Beery

   CV4Animals @ CVPR 2026

5. Bridging the Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs

   Somnath Kumar*, Vaibhav Balloli*, Mercy Ranjit, Tanuja Ganu, Kabir Ahuja, Sunayna Sitaraman, Kalika Bali

   COLING 2025 · Oral

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

   Vaibhav Balloli, Sara Beery, Elizabeth Bondi-Kelly

   IJCAI 2024 · Human-Centered AI track · <5% accept

7. Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception

   Anurag Ghosh, Vaibhav Balloli, Akshay Nambi, Aditya Singh, Tanuja Ganu

   NeurIPS 2023

Working papers

• To Ask or Not To Ask: Evaluating Information Seeking, Execution, and Abstention Capabilities in Long-Context LLM Agents

  Vaibhav Balloli, Elizabeth Bondi-Kelly

• Towards Improving Interactivity in Multi-Turn Human-Agent Systems

  Vaibhav Balloli, Hussein Mozannar, Adam Fourney, Gagan Bansal, Saleema Amershi, Eric Horvitz

Awards & honours

• 2026 FAccT travel award
• 2025 Exceptional preliminary exam (advancement to candidacy)
• 2025 Poster presented at the Society-centered AI workshop, Google, Mountain View
• 2024 2nd place, Google × MHacks hackathon
• 2024 VeLLM work referenced by Satya Nadella and covered in the Times of India and FirstPost
• 2023 Selected for the Harvard/MIT HAIST/MAIA introductory fellowship on AI safety
• 2022 HAMS automated licence testing featured in the Punjab News Express
• 2021 Winner, Microsoft Global Hackathon (Future of Edge Computing track)
• 2020 Co-founded SmartCampus, which handled ₹25 million in transactions

Service

• Conference reviewing

  NeurIPS 2026, KDD 2026, NeurIPS 2025, IJCAI 2025, ICML 2025, AAMAS 2025, ICLR 2025, NeurIPS 2024

• Workshop reviewing

  CV4Animals @ CVPR 2024, CompSust @ NeurIPS 2023, EvalEval @ ACL 2026