Ayush K. Rai

AI Research Scientist/Engineer with 5+ years of experience in multimodal AI, self-supervised learning and video understanding across academia and industry. Designed and implemented scalable deep learning systems for foundation models, video representation learning and generative modeling, with publications at CVPR, ICCV, WACV, and BMVC. Experienced in large-scale training and building efficient models for real-world data.

PhD in computer vision and deep learning from Insight Centre for Data Analytics, advised by Prof. Alan F. Smeaton and Prof. Noel O’Connor.

Research interests: Computer Vision, Machine Learning, Deep Learning, Video Understanding, Efficient computational methods, Multi-modal Learning: Vision + Language.

Prior to this, I was a graduate student at Ecole CentraleSupelec, University of Paris-Saclay, Paris pursuing M.Sc in Artificial Intelligence. I completed my master’s research Internship at Centre for Robotics, MINES ParisTech.

Currently I am actively looking for Full-time Machine Learning Researcher, Engineer or Scientist roles. Please get in touch to discuss more.

news

Aug 15, 2025	1 paper accepted at ICCV 2025 Workshop on Long Multi-Scene Video Foundations.
Apr 05, 2024	1 paper accepted at CVPR 2024 Workshop on Visual Anomaly and Novelty Detection (VAND 2.0).
Nov 05, 2023	1 paper accepted at BMVC 2023.
Sep 18, 2023	Attended ELLIS Large Scale AI 2023 Summer School, Modena, Italy.
Aug 30, 2023	Attended M^2L 2023 Summer School, Thessaloniki, Greece.
Oct 10, 2022	1 paper accepted at WACV 2023.

selected publications

ICCVW 2025

Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection

Ayush K. Rai, Kyle Min, Tarun Krishna , and 3 more authors

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops , Oct 2025

Bib PDF Code

@inproceedings{Rai_2025_ICCV,
  author = {Rai, Ayush K. and Min, Kyle and Krishna, Tarun and Hu, Feiyan and Smeaton, Alan F. and O'connor, Noel},
  title = {Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
  month = oct,
  year = {2025},
  pages = {7012-7022},
}

CVPRW 2024

Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach

Ayush K. Rai, Tarun Krishna, Feiyan Hu , and 4 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops , Jun 2024

Bib PDF Code

@inproceedings{Rai_2024_CVPR,
  author = {Rai, Ayush K. and Krishna, Tarun and Hu, Feiyan and Drimbarean, Alexandru and Mcguinness, Kevin and Smeaton, Alan F. and O'connor, Noel E.},
  title = {Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month = jun,
  year = {2024},
  pages = {3887-3899},
}

BMVC 2023

Unifying Synergies between Self-supervised Learning and Dynamic Computation

Tarun Krishna, Ayush K. Rai, Alexandru F Drimbarean , and 5 more authors

In 34th British Machine Vision Conference 2023, BMVC 2023, Aberdeen, UK, November 20-24, 2023 , Jun 2023

Bib PDF Code

@inproceedings{Krishna_2023_BMVC,
  author = {Krishna, Tarun and Rai, Ayush K. and Drimbarean, Alexandru F and Arazo, Eric and Albert, Paul and Smeaton, Alan and McGuinness, Kevin and Connor, Noel O},
  title = {Unifying Synergies between Self-supervised Learning and Dynamic Computation},
  booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
  publisher = {BMVA},
  year = {2023},
}

WACV 2023

Motion Aware Self-Supervision for Generic Event Boundary Detection

Ayush K. Rai, Tarun Krishna, Julia Dietlmeier , and 3 more authors

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , Jan 2023

Bib PDF Code

@inproceedings{Rai_2023_WACV,
  author = {Rai, Ayush K. and Krishna, Tarun and Dietlmeier, Julia and McGuinness, Kevin and Smeaton, Alan F. and O{\textquoteright}Connor, Noel E.},
  title = {Motion Aware Self-Supervision for Generic Event Boundary Detection},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  month = jan,
  year = {2023},
  pages = {2728-2739},
}