Portrait
Elkhan Ismayilzada
PhD Candidate
Computer Science and Engineering
Michigan State University
About Me

I am a PhD candidate in Computer Science and Engineering at Michigan State University. My current research interests include 3D reconstruction and physics-informed computer vision.

Research Interests: Computer Vision (3D reconstruction, motion recovery), Machine Learning (deep learning, meta-learning, incremental learning).

Education
  • Michigan State University
    Michigan State University
    PhD Candidate, Computer Science and Engineering
    Aug. 2024 - present
  • Ulsan National Institute of Science and Technology (UNIST)
    Ulsan National Institute of Science and Technology (UNIST)
    M.Sc. in Computer Science and Engineering
    Jul. 2024
  • Ulsan National Institute of Science and Technology (UNIST)
    Ulsan National Institute of Science and Technology (UNIST)
    B.Sc. in Computer Science and Engineering
    Jul. 2022
News
2026
PAD-Hand received a Highlight Paper award at CVPR 2026.
Apr 09
PAD-Hand is accepted to CVPR 2026.
Feb 20
2025
Passed the PhD Qualifying Examination at Michigan State University.
Oct 01
2024
QORT-Former is accepted to AAAI 2025.
Dec 09
Started my PhD in Computer Science and Engineering at Michigan State University.
Aug 16
Selected Publications (view all )
PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery
PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery

Elkhan Ismayilzada, Yufei Zhang, Zijun Cui

Computer Vision and Pattern Recognition (CVPR) 2026 Highlight

We propose a novel physics-aware conditional diffusion framework that refines noisy pose sequences into physically plausible hand motion while estimating the physics variance in motion estimates. .

PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery

Elkhan Ismayilzada, Yufei Zhang, Zijun Cui

Computer Vision and Pattern Recognition (CVPR) 2026 Highlight

We propose a novel physics-aware conditional diffusion framework that refines noisy pose sequences into physically plausible hand motion while estimating the physics variance in motion estimates. .

QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects
QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects

Elkhan Ismayilzada*, MD Khalequzzaman Chowdhury Sayem*, Yihalem Yimolal Tiruneh, Mubarrat Tajoar Chowdhury, Muhammadjon Boboev, Seungryul Baek (* equal contribution)

Association for the Advancement of Artificial Intelligence (AAAI) 2025

We present a query-optimized real-time Transformer (QORT-Former), the first Transformer-based real-time framework for 3D pose estimation of two hands and an object.

QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects

Elkhan Ismayilzada*, MD Khalequzzaman Chowdhury Sayem*, Yihalem Yimolal Tiruneh, Mubarrat Tajoar Chowdhury, Muhammadjon Boboev, Seungryul Baek (* equal contribution)

Association for the Advancement of Artificial Intelligence (AAAI) 2025

We present a query-optimized real-time Transformer (QORT-Former), the first Transformer-based real-time framework for 3D pose estimation of two hands and an object.

All publications