News

2025-08

Talk: Deconstructing Coding Agents

Delivered a talk on the architecture and capabilities of modern coding agents to C-suite executives and engineering leadership in Lahore.

2025-07

Released dPrune: A Framework for Data Pruning

dPrune is a Python library designed to make data selection and pruning simple and accessible for NLP and speech tasks.

2024-05

LLMs in Development Workflows - PyCon 2024

Presented at PyCon 2024 (PK) on integrating Large Language Models into software development workflows.

Publications

IEEE ACCESS 2025

A Survey on Data Selection for Efficient Speech Processing

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

ACL 2025 Workshop on GEM

The fellowship of the llms: Multi-agent workflows for synthetic preference optimization dataset generation

Samee Arif, Sualeha Farid, Abdul Hameed Azeemi, Awais Athar, Agha Ali Raza

COLING 2025

To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

EMNLP 2024 (Findings)

Generalists vs. Specialists: Evaluating Large Language Models for Urdu

Samee Arif, Abdul Hameed Azeemi, Agha Ali Raza, Awais Athar

ACL 2024 Workshop on Low-Resource Machine Translation

Challenges in Urdu Machine Translation

Abdul Basit, Abdul Hameed Azeemi, Agha Ali Raza

ACL 2024 (Findings)

Deepfake Defense: Constructing and Evaluating a Specialized Urdu Deepfake Audio Dataset

Sheza Munir, Wassay Sajjad, Mukeet Raza, Emaan Mujahid Abbas, Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

NeurIPS 2023 Workshop on Efficient Speech and Natural Language Processing

Representative Subset Selection for Efficient Fine-Tuning in Self-Supervised Speech Recognition

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

EMNLP 2023 (Findings)

Data Pruning for Efficient Model Pruning in Neural Machine Translation

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

INTERSPEECH 2023

Self-Supervised Dataset Pruning for Efficient Training in Audio Anti-spoofing

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

INTERSPEECH 2022

Dataset Pruning for Resource-constrained Spoofed Audio Detection

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

AALTD - ECML PKDD 2021

RevDet: Robust and Memory Efficient Event Detection and Tracking in Large News Feeds

Abdul Hameed Azeemi, Mohammad Hamza Sohail, Talha Zubair, Muaz Maqbool, Irfan Younas, Omair Shafiq

Portfolio

AI Agent with Tool Calling, Memory & RAG

Advanced AI agent with tool calling capabilities, memory, and Retrieval-Augmented Generation (RAG) for contextual responses.

TypescriptVercel AI SDKOpenAIRAGTool Calling

Smart Streaming Broadcast Manager

Managed the frontend, backend and shell scripting of an online streaming manager for 24/7 live-stream.

FrontendBackendShell ScriptingLive Streaming

Digitery Inventory

A web application for a company involved in textile business, managing multiple online Magento stores. Digitery Inventory was developed using AngularJS, Firebase, Magento 2 REST API, DHL XML Web Services and Call Courier API.

AngularJSFirebaseMagento 2 REST APIDHL XML Web ServicesCall Courier API

Agency App

An android application for digital agencies needing a simple yet effective project management and CRM solution. Agency App was built using Android, Firebase, Sinch API, Google Maps API and Firebase Cloud Functions.

AndroidFirebaseSinch APIGoogle Maps APIFirebase Cloud Functions

NCBA&E LCU Portal

Student portal for NCBA&E LCU Campus

ShootApp

Shoot is an application that uses device location to share pictures/videos with people nearby.

Eduver

A Career Counseling Portal for prospective college students.

Photographire

Online photographer hiring portal using custom built PHP framework where customers could directly book photographers, chat with them and provide ratings.

PHPCustom Framework

EduCaterers v1

Full-fledged online portal aimed at providing entry test preparation, deadlines, suggestions and linking universities to students.