avatar

Mahmoud Ahmed

M.S/Ph.D. Student
KAUST
mahmoud.ahmed (at) kaust.edu.sa


About Me

I am an MS/PhD student at KAUST, supervised by Dr. Mohamed Elhoseiny. I earned my bachelor’s degree from the American University in Cairo (AUC) 2022. My research focuses on multimodal large language models (LLMs) and enabling LLMs to develop real-life reasoning capabilities with grounding skills.

I am particularly interested in multimodal LLMs, compositional understanding, and vision foundation models.

News

Publications

  1. Kestrel: Point Grounding Multimodal LLM for Part-Aware 3D Vision-Language Understanding
    Junjie Fei*, Mahmoud Ahmed*, Jian Ding, Eslam Mohamed Bakr, Mohamed Elhoseiny (* Equal contribution)
    Under Review.
    PDF

  2. 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
    Mahmoud Ahmed, Xiang Li, Arpit Prajapati, Mohamed Elhoseiny
    The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Neurips), 2024.
    PDF Code

  3. 3DCoMPaT++: An improved Large-scale 3D Vision Dataset for Compositional Recognition
    Habib Slim, Xiang Li, Yuchen Li, Mahmoud Ahmed, Mohamed Ayman, Ujjwal Upadhyay, Ahmed Abdelreheem, Arpit Prajapati, Suhail Pothigara, Peter Wonka, Mohamed Elhoseiny
    Under review, TPAMI, 2024.
    PDF Code Project Page BibTex

  4. Cot3dref: Chain-of-thoughts data-efficient 3d visual grounding
    Eslam Abdelrahman, Mohamed Ayman, Mahmoud Ahmed, Habib Slim, Mohamed Elhoseiny
    The Eleventh International Conference on Learning Representations (ICLR), 2023.
    PDF Code Project Page BibTex