Hadi Alzayer

Hadi Alzayer

I am a Research Scientist at Google DeepMind.

Before that, I completed my PhD at the University of Maryland, co-advised by Jia-Bin Huang and Jiajun Wu, spending the latter half of my PhD at Stanford. Before my PhD, I was at Cornell, where I earned my BS (ECE and CS) and MS (CS) and was advised by Kavita Bala and Bharath Hariharan.

Publications

Masked Visual Actions for Unified World Modeling

Hadi Alzayer, Wenlong Huang, Haonan Chen, Christopher Luey, Lvmin Zhang, Maneesh Agrawala, Gordon Wetzstein, Li Fei-Fei, Yilun Du, Jiajun Wu, Jia-Bin Huang
Preprint 2026

Coupled Diffusion Sampling for Training-Free Multi-View Image Editing

Hadi Alzayer, Yunzhi Zhang, Chen Geng, Jia-Bin Huang, Jiajun Wu
CVPR 2026

Choreographing a World of Dynamic Objects

Yanzhe Lyu*, Chen Geng*, Karthik Dharmarajan, Yunzhi Zhang, Hadi Alzayer, Shangzhe Wu, Jiajun Wu
CVPR 2026

Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation

Hadi Alzayer, Philipp Henzler, Jonathan T. Barron, Jia-Bin Huang, Pratul P. Srinivasan, Dor Verbin
CVPR 2025Highlight

SimVS: Simulating World Inconsistencies for Robust View Synthesis

Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi Alzayer, Ruiqi Gao, Ben Poole, Jonathan T. Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul P. Srinivasan
CVPR 2025

Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos

Hadi Alzayer, Zhihao Xia, Xuaner (Cecilia) Zhang, Eli Shechtman, Jia-Bin Huang, Michael Gharbi
ACM Transaction on Graphics 2025

Seeing the World through Your Eyes

Hadi Alzayer*, Kevin Zhang*, Christopher Metzler, Jia-Bin Huang
CVPR 2024Oral, 3.3%

3D Motion Magnification: Visualizing Subtle Motions with Time-Varying Neural Fields

Brandon Y. Feng*, Hadi Alzayer*, Michael Rubinstein, William T. Freeman, Jia-Bin Huang
ICCV 2023

DC2: Dual-Camera Defocus Control by Learning to Refocus

Hadi Alzayer, Abdullah Abuolaim, Leung Chun Chan, Yang Yang, Ying Chen Lou, Jia-Bin Huang, Abhishek Kar
CVPR 2023 Two Minute Papers Video

AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning

Hadi Alzayer, Hubert Lin, Kavita Bala
IROS 2021Best Entertainment Paper Finalist

Recent Internships

  • Google DeepMind (Summer 2024)
    Research Intern (Hosted by Dor Verbin, Pratul Srinivasan, and Jon Barron)
  • Adobe (Summer 2023)
    Research Intern (Hosted by Michaël Gharbi)
  • Google (Summer 2022)
    Research Intern on the Pixel Camera Team (Hosted by Abhishek Kar and Ryan Chan)
  • Apple (Summer 2021)
    ML Engineering Intern

Outside of research..

I believe that endurance activities are perfect for conditioning the mind to handle any challenges in life. Here is a list of some of my recent activities:

  • [08/17/2025] Rae Lakes Loop trail run (~40 miles)
  • [08/02/2025] Summitting Glacier Peak in WA (Thanks Ricardo for taking me!)
  • [04/25/2025] Canyons 100 Miler (Finished!; 32 hours)
  • [10/18/2024] Appalachian Trail Four-State Challenge
  • [07/15/2023] Tahoe Rim Trail 100 Miler (DNF; at mile 59. Unfortunate..)
  • [07/15/2023] Tahoe Rim Trail 100 Miler (Finished!; 35 hours)
  • [06/10/2023] Mt. Umunhum 52 Miler
  • [12/18/2022] Appalachian Trail Four-State Challenge
  • [11/19/2022] JFK 50 Mile run
  • [08/07/2022] Skyline 50k
  • [07/16/2022] Tahoe Rim Trail 100 Miler (DNF; completed 80 miles out of 102)
  • [06/11/2022] Mt. Umunhum 50k
  • [11/20/2021] JFK 50 Mile run
  • [10/11/2021] Biking up Whiteface Mountain
  • [09/04/2021] Lake George Half-IRONMAN distance triathlon
  • [07/10/2021] Mt. Hood 50k run