Ahmad Rahimi

PhD candidate at VITA, EPFL

prof_pic.jpg

I am a PhD candidate at EPFL advised by Prof. Alexandre Alahi, specializing in efficient video generation, driving world models, and 3D/4D scene reconstruction. I will complete my PhD in February 2027 and am interested in research scientist and research engineer opportunities beginning in March 2027.

I received my B.Sc. in Computer Science from Sharif University of Technology in Iran in 2022.

news

May 09, 2026 My Applied Science internship at Wayve in London has concluded. I am grateful to the team for an excellent experience working on the challenges of autonomous driving.
Feb 21, 2026 My recent project on motion appearance decoupling for driving world models was accepted to CVPR 2026!
Dec 05, 2025 Received an ARC Prize Honorable Mention for research on repurposing video diffusion models for novel visual and logic tasks.
Nov 24, 2025 I joined Wayve as an Applied Science Intern, working on GAIA-related projects. I am excited to contribute to the future of autonomous driving with this team!
Feb 26, 2025 Two of my papers were accepted to CVPR 2025!

selected publications

  1. CVPR
    mad-pull_video.gif
    MAD: Motion Appearance Decoupling for efficient Driving World Models
    Ahmad Rahimi*, Valentin Gerard*, Eloi Zablocki, Matthieu Cord, and Alexandre Alahi
    2026
    arXiv Code Website
  2. CVPR
    gem-control.gif
    GEM: A Generalizable Ego-vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
    Mariam Hassan*, Sebastian Stapf*, Ahmad Rahimi*, Pedro M B Rezende, Yasaman Haghighi, and 15 more authors
    2025
    arXiv Code Website
  3. ICML
    gen2gen.png
    From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models
    Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, and 2 more authors
    2026
    ARC Prize 2025 Honorable Mention Abs arXiv Code Website
  4. CVPR
    social-causality.jpg
    Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations
    Ahmad Rahimi, Po-Chien Luan, Yuejiang Liu, Frano Rajič, and Alexandre Alahi
    2025
    arXiv Code
  5. CVPR
    scene-attack.gif
    Vehicle trajectory prediction works, but not everywhere
    Mohammadhossein Bahari, Saeed Saadatnejad, Ahmad Rahimi, Mohammad Shaverdikondori, Amir-Hossein Shahidzadeh, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    arXiv Code Website