I'm a PhD student in Machine Learning and Systems at Virginia Tech SNAIL Lab, advised by Dr. Bo Ji. My research centers around optimizing machine learning workloads for systems, exploring techniques like efficient self-attention, token dropping, quantization, and many more to make AI more accessible for edge and commodity devices. Prior to starting my PhD, I worked as an ML Engineer at A Fortune 500 Company where I worked on building and deploying their AI-driven recommendation systems for pharmaceutical companies. Beyond research, I actively contribute to the academic community. I served as Secretary for the Virginia Tech CS Graduate Council in 2024-25. Additionally, I served as a reviewer for workshops at ICLR, CVPR and volunteered at AAAI.
Machine Learning and Systems Researcher
Phd Student at Virginia Tech
Interested in Optimization of ML workloads
Email: hasanarif [at] vt [dot] edu
Phone: +1 540 449 6919
Office: Gilbert Place, Room 4215
Address: 220 Gilbert Street, Blacksburg, VA 24060
News
- [Mar 2025] I got selected as 2025 CCI SWVA Cyber Innovation Scholar and received $1500 grant!!!
- [Mar 2025] I got featured by Commonwealth Cyber Initiative Southwest Virginia in their official LinkedIn.
- [Feb 2025] I met Andrew Ng. One of the top moments in AAAI 2025 for me!.
- [Feb 2025] I presented my first-author paper at AAAI 2025 in Philadelphia, PA. [Image]
- [Jan 2025] I made a view demo for my AAAI 2025 paper. Check that out in Youtube!
- [Jan 2025] I passed my PhD Qualifying Exam. One step closer to the PhD!
- [Aug 2024] My first "first-author" paper has been accepted at AAAI 2025!!! See you in Philly!
- [Aug 2024] I attended Artificial Intelligence Modeling, Analysis, and Control of Complex Systems Workshop in Columbus, OH. Thanks to my advisor for the invitation!
- [Jul 2024] I attended the MLSys 2024 conference in Santa Clara, California.
- [Jun 2024] I got selected as 2024 CCI SWVA Cyber Innovation Scholar and received $2000 grant!!!
- [Aug 2023] I started my PhD in Virginia Tech Dept. of Computer Science.
- [Mar 2023] I received best project presentation award in Fusemachines H&M AI Fellowship program.
- [May 2022] I have joined IQVIA Next Best Action team as Machine Learning Engineer.
- [May 2022] I defended my undergraduate thesis titled "Generate 3D Bone from DICOM using Deep CNN".
Research and Publications
Peer-reviewed- HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models by Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Deepu John, Bo Ji, Proceedings of the 2025 AAAI Conference on Artificial Intelligence in Philadelphia, Pennsylvania [paper] [code]
- PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model by Kazi Hasan Ibn Arif, Sajib Acharjee Dip, Khizar Hussain, Lang Zhang, Chris Thomas Proceedings of the 2025 CVPR Workshop for Trustworthiness in Multi-Modal Open-World Intelligence in Nashville TN, United States. [paper] [code]
- Equitable Skin Disease Prediction Using Transfer Learning and Domain Adaptation by Sajib Acharjee Dip, Kazi Hasan Ibn Arif, Uddip Acharjee Shuvo, Ishtiaque Ahmed Khan, Na Meng Proceedings of the 2024 AAAI Conference on Artificial Intelligence Machine Intelligence for Equitable Global Health (MI4EGH) Workshop in Arlington, Virginia [paper]
- Local and Global Feature Based Hybrid Deep Learning Model for Bangla Parts of Speech Tagging by Muntasir Hoq, Kazi Hasan Ibn Arif, Mohammed Nazim Uddin Proceedings of 2021 2nd International Conference for Emerging Technology (INCET) in Belagavi, India [paper]
- Generate 3D Bone from DICOM using Deep CNN by Kazi Hasan Ibn Arif, Jainta Paul, Dr. Mahmuda Naznin Undergraduate Thesis [paper]