Ainaz Eftekhar

I am a PhD student at the University of Washington in Computer Science and Engineering supervised by Prof. Ali Farhadi and Prof. Ranjay Krishna (RAIVN Lab).

In the summers of 2023 and 2024, I was a research intern with the PRIOR team at the Allen Institute for AI (AI2), where I worked closely with Kuo-Hao Zeng and Kiana Ehsani.

Previously, I received my Bachelor of Science in Computer Engineering from Sharif University of Technology. During the final year of my bachelor's program, I was a visiting student at EPFL where I worked in VILAB under the supervision of Prof. Amir Zamir.

My research interests lie in the intersection of computer vision, machine learning, and embodied-AI.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github  /  LinkedIn

profile photo

News
  • 08/2024: Accepted for UW + Amazon Science Hub Fellowship (1 year of funding)
  • 06/2024: Starting my internship with the PRIOR team at Allen Institute for AI (AI2)
  • 01/2024: "Selective Visual Representations Improve Convergence and Generalization for Embodied-AI" has been accepted as ICLR 2024 [Spotlight, 5%]
  • 06/2023: Starting my internship with the PRIOR team at Allen Institute for AI (AI2)
Publications & Preprints
The One RING Logo : a Robotic Indoor Navigation Generalist
Ainaz Eftekhar, Luca Weihs, Rose Hendrix, Ege Caglar, Jordi Salvador, Alvaro Herrasti, Winson Han, Eli VanderBilt, Aniruddha Kembhavi, Ali Farhadi, Ranjay Krishna Kiana Ehsani*, Kuo-Hao Zeng*
under submission
project page / arXiv / code [coming soon]

RING is an embodiment-agnostic policy, trained solely in simulation with diverse randomly initialized embodiments at scale. RING generalizes to diverse real-world embodiments despite being trained exclusively in simulation without access to the real robot configurations.

Selective Visual Representations Improve Convergence and Generalization for Embodied-AI
Ainaz Eftekhar*, Kuo-Hao Zeng*, Jiafei Duan, Ali Farhadi, Ani Kembhavi, Ranjay Krishna
ICLR, 2024 [Spotlight]
project page / arXiv / code

Inspired by selective attention in humans—the process through which people filter their perception based on their experiences, knowledge, and the task at hand—we introduce a parameter-efficient approach to filter visual stimuli for Embodied-AI.

Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans
Ainaz Eftekhar*, Alexander Sax*, Roman Bachmann, Jitendra Malik, Amir Zamir
ICCV, 2021
project page / arXiv / code

A pipeline to resample comprehensive 3D scans from the real-world into static multi-task vision datasets.

Puzzle-AE: Novelty Detection in Images Through Solving Puzzles
Mohammadreza Salehi, Ainaz Eftekhar* Niousha Sadjadi, Mohammad Hossein Rohban, Hamid R. Rabiee
arXiv , 2020
arXiv / code

A self-supervised approach to Anomaly Detection.

Honors & Awards
  • 2024: UW + Amazon Science Hub Fellowship (1 year of funding)
  • 2021: EPFL Summer Research Fellowship: Ecole polytechnique federale de Lausanne
  • 2020: Top 5% Academic Ranking: Sharif University of Technology
  • 2016-2015: Bronze Medal: Iranian National Math Olympiad
  • 2013: Gold Medal in the 9th International Mathematics Contest: IMC (Singapore) [certificate]

Design and source code from Jon Barron's website.