Mohammad Mohammadi

I am a Ph.D. student in Computer Science at the University of Toronto, where I am advised by Prof. Igor Gilitschenksi. I’m currently a research intern at the Samsung AI Center in Toronto. Previously, I interned at the Robot Learning Lab at the University of Freiburg.

I received my Bachelor's degree in Computer Engineering from Sharif University of Technology. During my Bachelor, I had the chance to intern at EPFL, Max-Planck Institute, and CUHK.

Email  /  CV  /  Google Scholar  /  Github

profile photo

Research

Generally, I am interested in designing intelligent systems, e.g. active agents, with high performance in real-world. My current research spans low-level vision (event-based vision, computational photography) and robotics.

News

  • 📣 June 2025: MORE is accepted at IROS 2025! 🎉
  • 📢 June 2025: MORE is accepted at RSS 2025 Workshop on Mobile Manipulation!
  • 🚀 May 2025: I’ve joined Samsung Toronto AI Center as a full-time research intern.

Publications and Pre-prints
MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning
Mohammad Mohammadi *, Daniel Honerkamp*, Martin Büchner*, Matteo Cassinelli*, Tim Welschehold, Fabien Despinoy, Igor Gilitschenski, Abhinav Valada
IROS, 2025
project page, code (coming soon)

We tackle mobile manipulation rearrangement tasks from the Behavior-1k dataset, where a robot is required to solve complex tasks requiring exploration, navigation, and manipulation in multi-room environments. The goal is to rearrange objects in a scene based on natural language instructions. We introduce MORE, a novel framework that leverages a large language model to reason about high-level planning, combined with low-level real-world subpolicies.
Implicit Poisoning Attacks in Two-Agent Reinforcement Learning...
Mohammad Mohammadi *, Jonathan Nöther *, Debmalya Mandal, Adish Singla, Goran Radanovic
AAMAS, 2023

We study targeted poisoning attacks in a two-agent setting, where an attacker implicitly poisons the effective environment of one agent by modifying the policy of its peer. We provide the computational complexity analysis alongside an approximate algorithm.

PALMER: Perception-Action Loop with Memory for Long-Horizon Planning
Onur Beker, Mohammad Mohammadi, Amir Zamir
NeurIPS, 2022
project page

We introduce PALMER, a long-horizon planning method that directly operates on high-dimensional sensory input observable by an agent on its own (e.g., images from an onboard camera).

More about me!

I’m a big fan of stand-up comedy (Dave Chappelle and Bill Burr are my all-time favorites). I enjoy playing tennis, reading non-fiction, and cooking Persian dishes. I'm also on a mission to find the best coffee in Toronto ☕.

Design and source code from Jon Barron's website.