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.
FSE 2025 / PACMSE - 2025
Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions
Shaila Sharmin, Anwar Hossain Zahid, and collaborators
Introduces Soft Assertions, a method for detecting and triggering hidden numerical instability bugs in machine learning applications.
arXiv:2502.19612 - 2025
Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization
Anwar Hossain Zahid, Monoshi Kumar Roy, and collaborators
Evaluates how large language models perform on hate speech detection when geographic and social context are included.
arXiv:2410.09172 - 2024
Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs
Anwar Hossain Zahid, Ignacio Laguna, Wei Le
Studies numerical differences between NVIDIA and AMD GPU executions and their implications for reproducibility and portability.
ICCIT 2020 - 2020
A Conceptual Design of Virtual Internship System
Raihan Mia, Anwar Hossain Zahid, and collaborators
Presents a conceptual software platform for virtual internship delivery and software development skill benchmarking.
Projects
Implementation work.
Systems and applied projects from research, national lab work, industry, and advanced coursework.
Python, PyTorch, TensorFlow
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.
C++, HIP, CUDA, LLVM
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.
Python, Transformers, HuggingFace, Scikit-learn
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.
Python, OpenCV, Dlib, FaceNet
Face Recognition with Liveliness Detection
Developed a real-time face recognition and spoof detection system for FinTech applications, enhancing security for remote banking verification.
Java, Spring Boot, OAuth 2.0, JWT
Parliament Resource Planning – SSO Integration
Implemented Single Sign-On authentication for PRP system, enabling secure unified access across parliamentary resource modules.
Python, Scikit-learn, Transformers
COM S 572 – Machine Learning Project
Implemented and evaluated ML algorithms for natural language processing tasks. Later extended for LLM experiments and paper publication.
Python, Minimax, Alpha-Beta Pruning
Othello AI Agent
Developed an intelligent Othello game-playing agent using adversarial search algorithms and heuristic evaluation functions.
Java
Mancala Game Simulation
Created a Mancala game engine with an AI opponent using minimax and heuristic strategies.
C++
Ray Tracing Renderer
Built a ray tracing engine from scratch to render 3D scenes with reflection, refraction, and shading.
C++, Operating Systems
Nachos – Instructional Operating System
Extended the Nachos instructional OS to implement thread scheduling, virtual memory, and file system operations.
Python, NumPy, Signal Processing
Channel Equalization for Wireless Communication
Implemented and tested channel equalization algorithms to improve signal quality in noisy communication environments.