Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions
Introduces Soft Assertions, a method for detecting and triggering hidden numerical instability bugs in machine learning applications.
Publications
Research on reliable ML, numerical debugging, and AI evaluation.
Peer-reviewed and preprint work spanning machine learning reliability, GPU numerical correctness, LLM evaluation, and software engineering education.
Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization
Evaluates how large language models perform on hate speech detection when geographic and social context are included.
Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs
Studies numerical differences between NVIDIA and AMD GPU executions and their implications for reproducibility and portability.
A Conceptual Design of Virtual Internship System
Presents a conceptual software platform for virtual internship delivery and software development skill benchmarking.