Publications and Pre-prints
|
TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
Mohammad Mohammadi, Ziyi Wu, Igor Gilitschenksi
ICCV, 2025
project page, code (coming soon)
We propose TESPEC, a self-supervised pretraining framework designed to capture long-term spatio-temporal information from event data.
Unlike existing approaches that pretrain feedforward models on short event streams, TESPEC is tailored for recurrent models and leverages long event sequences.
Using a masked image modeling strategy and a novel event accumulation method, TESPEC reconstructs pseudo-grayscale videos.
Our model achieves state-of-the-art performance in downstream tasks such as object detection, semantic segmentation, and monocular depth estimation
|
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).
|
