Shravan Chaudhari
PhD Student, Computer Science
Johns Hopkins University
I am a Computer Science PhD student at Johns Hopkins University, advised by Prof. Rama Chellappa and Prof. Suchi Saria. My research is on trustworthy machine learning: I work on LLM agents for code understanding, graph-informed retrieval, domain adaptation, and out-of-distribution detection.
Previously, I received my MS from NYU Courant and BE from BITS Pilani. I currently work part-time with the GitHub Copilot Science team at Microsoft, and have previously interned at Amazon and Johnson & Johnson MedTech.
News
- Feb 2026New preprint with Prakhar Kaushik on shared LoRA subspaces for continual learning, with Profs. Chellappa and Yuille. [arXiv]
- Jan 2026Started as a Student Researcher with the GitHub Copilot Science team at Microsoft.
- Dec 2025Three preprints out: Open-Set Domain Adaptation Under Background Distribution Shift, The Universal Weight Subspace Hypothesis, and SpIDER for issue localization in code graphs.
- Sep 2025Wrapped up an Applied Scientist II internship with the Amazon Coding Agents team.
- Jun 2025EigenLoRAx presented at the CVPR 2025 Workshops.
- Apr 2025Paper accepted to TMLR: rethinking time encoders for dynamic graph learning.
- May 2023Joined the JHU CS PhD program, advised by Prof. Rama Chellappa and Prof. Suchi Saria.
Research interests
Trustworthy and fair machine learning · LLM agents and code understanding · Graph-informed retrieval-augmented generation · Domain adaptation under distribution shift · Out-of-distribution and novel-category detection.
Publications
* denotes equal contribution. For a full list, see my Google Scholar.
2026
2025
2025
2025
2025
2025
2025
2024
PKDD
2024
Sci. Rep.
2024
2023
2021
2021
Experience
-
Jan 2026 – PresentStudent Researcher, Microsoft
CoreAI · GitHub Copilot Science team
GRPO-based RL fine-tuning and graph-aware scaffoldings for code repository navigation with cost-efficient LLMs. -
May 2025 – Sep 2025Applied Scientist II Intern, Amazon
Coding Agents team
LLM-driven dense embedding retrieval and code-graph navigation for GitHub-style issue localization across Python, Java, JS, TS. -
Aug 2024 – Dec 2024Applied Scientist II Intern, Amazon
Search Experience team
Multimodal LLM feedback and a novel metric for measuring search-page impact, validated against human annotators. -
May 2022 – Dec 2022ML & Software Co-Op, Johnson & Johnson MedTech
Algorithms & AI team
Semi-supervised active learning for surgical-robot video curation; cut annotation cost by over 70% while improving tool detection. -
Jan 2023 – May 2023Research Assistant, NYU Center for Data Science
Advisor: Prof. Jacopo Cirrone
Self-supervised representation learning for histopathology under unknown distributions. -
May 2021 – Oct 2021NSF / IRIS-HEP Fellow, Princeton Institute of Computational Science & Engineering
Graph neural networks for tau-particle identification; lifted ROC-AUC from 0.70 to 0.85. -
Sep 2020 – May 2021Student Researcher, CERN (Undergraduate Thesis)
Deep CNNs for high-energy particle classification with raw LHC detector images.
Education
-
2023 – PresentPhD, Computer Science, Johns Hopkins University
Advisors: Prof. Rama Chellappa, Prof. Suchi Saria · GPA 4.0/4.0 -
2021 – 2023MS, Computer Science, New York University (Courant)
CGPA 3.83/4.0 -
2017 – 2021BE, Electronics & Instrumentation, BITS Pilani
GPA 8.52/10
Teaching
- CSCI-GA 2271 Graduate Computer Vision (Prof. Rob Fergus, NYU) — Course Tutor
- CSCI-UA 472 Artificial Intelligence (NYU) — Course Assistant
- CSCI-UA 479 Data Management & Analysis (NYU) — Course Assistant
Mentoring & Service
- Mentor & Organizer, Machine Learning for Science — mentored three Google Summer of Code 2022 students.
- Google Summer of Code 2020 & 2021 — graph- and end-to-end ML frameworks for CERN/CMSSW.
- Talk: Accelerating End-to-End Deep Learning for High-Energy Particle Identification using GNNs, NSF IRIS-HEP Fellowship, 2021.