avatar

Mohamed Elmoghany

Machine Learning Research Scientist Intern @ Adobe Research
US Citizen
San Jose, CA

m.osama.elmoghany@gmail.com


About Me

I am currently a research intern at Adobe Research, supervised by Franck Dernoncourt (MIT PhD). Previously, I was a research intern at King Abdullah University of Science and Technology (KAUST) supervised by Prof. Mohamed Elhoseiny

I have over 10 years of mixed industry experience in machine learning, software and hardware. I started 3 startups, worked for Intel as a Design and Automation Engineer, and worked for Sonics Inc (acquired by Meta) as a Solutions Architect. I studied Computer Science at San Jose State University and received my BSc. in Electronics and Communications Engineering from Alexandria University.

Research Interests

News

Publications [Google Scholar]

  1. Top tier conference
    MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
    Sanjoy Chowdhury, Mohamed Elmoghany, Yohan Abeysinghe, Junjie Fei, Sayan Nag, Salman Khan, Mohamed Elhoseiny, Dinesh Manocha
    Good feedback @ top tier conference
    PDF Project Page
  2. ICCV'25
    A Survey on Long-Video Storytelling Generation, Architectures, Consistency, and Cinematic Quality
    Mohamed Elmoghany, Ryan Rossi, Seunghyun Yoon, Subhojyoti Mukherjee, Eslam Bakr, Puneet Mathur, Gang Wu, Viet Dac Lai, Nedim Lipka, Ruiyi Zhang, Varun Manjunatha, Chien Nguyen, Daksh Dangi, Abel Salinas, Mohammad Taesiri, Hongjie Chen, Xiaolei Huang, Joe Barrow, Nesreen Ahmed, Hoda Eldardiry, Namyong Park, Yu Wang, Jaemin Cho, Anh Totti Nguyen, Zhengzhong Tu, Thien Nguyen, Dinesh Manocha, Mohamed Elhoseiny, Franck Dernoncourt
    International Conference on Computer Vision, Workshop on Long Multi-Scene Video Foundations, Generation, Understanding and Evaluation, 2025
    PDF
  3. ICITST'11
    FPGA implementation of high speed XTS-AES for data storage devices
    Mohamed Elmoghany, Mohamed Diab, Moustafa Kassem, Mustafa Khairallah, Omar El Shahat, Wael Sharkasy
    International Conference for Internet Technology and Secured Transactions, 2011
    PDF Project Page During undergrad!

Paper Implementations and Research Projects

  1. Multimodal Vision Language Model implemented from Scratch **Mar'25**
    PDF Code

  2. Finetuning SD with LoRA (Low Rank Adaptation) **Jan'25**
    PDF Code

  3. Denoising Diffusion Implicit Mode (DDIM) and Classifier-Free Guidance (CFG) **Jan'25**
    PDF Code

  4. DDPM (Denoising Diffusion Probabilistic Model) **Jan'25**
    PDF Code

  5. Finetuning SD with ControlNet **Jan'25**
    PDF Code

  6. Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning (from scratch using Vision Transformer) **Oct'24**
    PDF Code Project Page

  7. A Neural Algorithm of Artistic Style **Sep'24**
    PDF Code Project Page

  8. Attention is all you need (from scratch with PyTorch) **Sep'24**
    PDF Code Project Page

  9. Healthcare Speech Recognition via Youtube Videos + video demo **Nov'23**
    PDF Code

  10. LLM Pruning **Nov'24**
    PDF Code

  11. LLM 4bit Quantization **Nov'24**
    PDF Code

Academic and Industry Experience



(updated Jul'25) create your website using this template