Saipraneeth Devunuri

Profile

I'm a Senior AI Scientist at Optym, where I develop AI-driven solutions to tackle complex transportation and logistics challenges. Previously, I was a PhD student in Transportation Engineering at the University of Illinois, Urbana-Champaign, where I focused on applying Large Language Models and Computer Vision to transportation data.

During my PhD, I worked closely with Professor Lewis Lehe on projects such as TransitGPT, a framework for querying transit data using natural language, and on automated parking lot detection from satellite imagery. My research emphasized making transportation data more accessible and developing practical tools to support urban planning and operations.

My work spans natural language processing, computer vision, and transportation engineering, with publications on ridesplitting effects in Chicago and infrastructure crack detection benchmarks. I'm especially interested in how AI can democratize access to transportation data and improve decision-making in the public and private sectors.

Publications

TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models

TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models

Saipraneeth Devunuri, Lewis J. Lehe

A Pipeline and NIR-Enhanced Dataset for Parking Lot Segmentation

A Pipeline and NIR-Enhanced Dataset for Parking Lot Segmentation

Shirin Qiam, Saipraneeth Devunuri, Lewis J. Lehe

WACV 2025

ChatGPT for GTFS: Benchmarking LLMs on GTFS Understanding and Retrieval

ChatGPT for GTFS: Benchmarking LLMs on GTFS Understanding and Retrieval

Saipraneeth Devunuri, Shirin Qiam, Lewis J. Lehe

Public Transport 2024

Bus stop spacing statistics: Theory and evidence

Bus stop spacing statistics: Theory and evidence

Saipraneeth Devunuri, Shirin Qiam, Lewis J. Lehe, Ayush Pandey, Dana Monzer

Journal of Public Transportation 2024

Taxation of ridehailing in the United States

Taxation of ridehailing in the United States

Lewis J Lehe, Saipraneeth Devunuri, Javier Rondan, Ayush Pandey, Daniel Vignon

Transport Policy 2024

A Survey of Errors in GTFS Static Feeds from the United States

A Survey of Errors in GTFS Static Feeds from the United States

Saipraneeth Devunuri, Lewis Lehe

Transport Findings 2024

Scale effects in ridesplitting: A case study of the City of Chicago

Scale effects in ridesplitting: A case study of the City of Chicago

Hao Liu, Saipraneeth Devunuri, Lewis J. Lehe, V. Gayah

Transportation Research Part A: Policy and Practice 2023

CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworks

CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworks

Shreyas Kulkarni, Shreyas Singh, Dhananjay Balakrishnan, Siddharth Sharma, Saipraneeth Devunuri, Sai Chowdeswara Rao Korlapati

ECCV Workshops 2022

An unsupervised learning framework for detecting adaptive cruise control operated vehicles in a vehicle trajectory data

An unsupervised learning framework for detecting adaptive cruise control operated vehicles in a vehicle trajectory data

Mohammadreza Khajeh-Hosseini, Alireza Talebpour, Saipraneeth Devunuri, Samer H. Hamdar

Expert systems with applications 2022