Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions
Shaila Sharmin, Anwar Hossain Zahid, et al. A method for finding hidden numerical instability bugs in ML applications.
Works
Research papers, systems, and applied software projects.
A focused view of my work across AI reliability, numerical debugging, LLM evaluation, GPU numerics, and production software engineering.
Publications
Selected papers.
Peer-reviewed and preprint work spanning reliable ML, model evaluation, and numerical correctness.
Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization
Anwar Hossain Zahid, Monoshi Kumar Roy, et al. Evaluates context-sensitive LLM behavior for hate speech detection.
Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs
Anwar Hossain Zahid, Ignacio Laguna, Wei Le. Cross-platform GPU numerical analysis for heterogeneous systems.
A Conceptual Design of Virtual Internship System
Raihan Mia, Anwar Hossain Zahid, et al. A software engineering education and benchmarking platform concept.
Projects
Implementation work.
Systems and applied projects from research, national lab work, industry, and advanced coursework.
Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions
FSE 2025 paper introducing Soft Assertions to detect and trigger numerical instability bugs in ML applications.
GPU Numerical Testing – HIP Code Generation in Varity
Contributed to the LLNL Varity project by implementing HIP backend generation for GPU kernel testing, enabling cross-platform numerical consistency evaluation.
Hate Speech Detection with Geographical Context
Extended a class project to evaluate hate speech detection models using geographical metadata. Later adapted for large language model testing and published in 2025.
Face Recognition with Liveliness Detection
Developed a real-time face recognition and spoof detection system for FinTech applications, enhancing security for remote banking verification.
Parliament Resource Planning – SSO Integration
Implemented Single Sign-On authentication for PRP system, enabling secure unified access across parliamentary resource modules.
COM S 572 – Machine Learning Project
Implemented and evaluated ML algorithms for natural language processing tasks. Later extended for LLM experiments and paper publication.
Othello AI Agent
Developed an intelligent Othello game-playing agent using adversarial search algorithms and heuristic evaluation functions.
Mancala Game Simulation
Created a Mancala game engine with an AI opponent using minimax and heuristic strategies.
Ray Tracing Renderer
Built a ray tracing engine from scratch to render 3D scenes with reflection, refraction, and shading.
Nachos – Instructional Operating System
Extended the Nachos instructional OS to implement thread scheduling, virtual memory, and file system operations.
Channel Equalization for Wireless Communication
Implemented and tested channel equalization algorithms to improve signal quality in noisy communication environments.