Toward more dependable software and AI

Selected Papers

IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models

FSE '25

µPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults

ICSE '25

An LLM-Based Agent-Oriented Approach for Automated Code Design Issue Localization

ICSE '25

Mock Deep Testing: Toward Separate Development of Data and Models for Deep Learning

ICSE '25

Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment

ICSE '24

Fairify: Fairness Verification of Neural Networks

ICSE '23

Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement

ICSE '23

Towards Understanding Fairness and its Composition in Ensemble Machine Learning

ICSE '23

23 Shades of Self-Admitted Technical Debt: An Empirical Study on Machine Learning Software

ESEC-FSE '22

The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large

ICSE '22

Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules

ICSE '22

DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs

ICSE '22

Manas: Mining Software Repositories to Assist AutoML

ICSE '22

Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline

ESEC-FSE '21

On Decomposing a Deep Neural Network into Modules

ESEC-FSE '20

Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness

ESEC-FSE '20

Repairing Deep Neural Networks Fix Patterns and Challenges

ICSE '20

BCFA Bespoke Control Flow Analysis for CFA at Scale

ICSE '20

A Comprehensive Study on Deep Learning Bug Characteristics

ESEC-FSE '19

News