Udayan Khurana — accepted AI-conference papers

2026

ADP-MA: An Interactive System for Autonomous Data Processing using Meta-Agents

IJCAI 2026

We demonstrate ADP-MA (Autonomous Data Processing using Meta-Agents), a system that autonomously solves a complex and diverse set of data processing tasks. Three domain-agnostic meta-agents coordinate task-specific ground agents through a multi-stage pipeline: data understanding, planning, critique,

Cited by 0 Scholar ↗

2023

SemFORMS: Automatic Generation of Semantic Transforms By Mining Data Science Code

Ibrahim Abdelaziz, Julian Dolby, Udayan Khurana, Horst Samulowitz, Kavitha Srinivas

IJCAI 2023poster

Careful choice of feature transformations in a dataset can help predictive model performance, data understanding and data exploration. However, finding useful features is a challenge, and while recent Automated Machine Learning (AutoML) systems provide some limited automation for feature engineering…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗