I am a final-year Ph.D. candidate in Computer Science at Lehigh University's P.C. Rossin College of Engineering, advised by Dr. Brian D. Davison.

My research is focused on a critical challenge at the forefront of modern AI: making powerful foundation models for computer vision both efficient and effective for on-device deployment. I specialize in developing novel, lightweight architectures that push the boundaries of what's possible on edge devices, without compromising on performance, robustness, or image quality.

Since 2022, I have been fortunate to collaborate closely with the Computational Photography and Generative AI teams (including Lenovo Research, Motorola Mobility). Where, I have contributed to developing and optimizing next-generation AI models for image enhancement and controllable restoration, directly tackling real-world challenges in the mobile and edge computing space.

I hold Master of Science and Bachelor of Science degrees in Computer Science, which have provided me with a strong and comprehensive foundation in AI and its applications. I am passionate about tackling complex problems, collaborating with creative teams, and translating cutting-edge research into impactful technology.

For Recruiters:

I am actively seeking full-time roles broadly at the intersection of Computer Vision and Machine Learning, suitable for a PhD graduate, with expected availability from late Fall 2025 onward.

News 📣

• [06.2024] Our paper Unified-EGformer got accepted in ICPR 2024.
• [07.2024] Our paper BiomedGPT got accepted in Nature Medicine, 2024.
• [06.2024] Our paper ExpoMamba got accepted in ICML Efficient Systems for Foundation Models, 2024.
• [06.2024] Joining Motorola’s Computational Photography team at Lenovo Research for Generative AI based research.
• [05.2024] I will be serving as a reviewer for ICML ES-FoMo-II 2024 and CIKM 2024.
• [12.2023] We released a new survey on Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts!
• [05.2023] The first preprint of BiomedGPT: A Unified and Generalist Biomedical Generative Pre-trained Transformer for Vision, Language, and Multimodal Tasks is released. Journal print soon to be released!
• [03.2023] Served as a reviewer for PeerJ.
• [01.2023] Joined Lenovo Research, Mobile Technology Innovation (MTI) Lab’s Computer Vision team work on developing AI models for Thinkpad camera lighting enhancements.
• [11.2021] Paper from my internship at Berkeley Lab won the Best Paper Award in SC2021.

Currently reviewing: Pattern Recognition
Previously reviewed papers at: ICLR, Pattern Recognition, WACV (Emergency), Big Data, SIGIR, WSDM, ICML, CIKM, PeerJ.

“Try to learn something about everything and everything about something” – Thomas Henry Huxley

“Inventing new things requires a type of skill and ability that you're not going to get from LLMs” – Yann LeCun