Sam Motamed

I am an ELLIS Ph.D. student at INSAIT where I am advised by Prof. Luc Van Gool and currently a Machine Learning Researcher Intern at Netflix. From May to November 2024, I was a Student Researcher at Google DeepMind in Toronto, working with Robert Geirhos.

Before my PhD journey began, I was a visiting researcher from 2021 to 2023 at CMU's Human Sensing Lab working with the amazing Fernando De La Torre. I also spent 7 wonderful years at the University of Toronto's Computer Science department where I earned my HBSc and MS degrees.

Email / CV / Google Scholar / Twitter / Github

7 Magic Mountains - Nevada

WACV 2026 - Arizona

Research

I'm broadly interested in Generative Vision models for content creation, and currently focused on Video synthesis. My research aims to gain a better understanding of how to enable user-intuitive control over Generative models. I am also interested in bias mitigation and harnessing the power of large vision and language models by adapting them to solve personalized tasks using limited data. Relevant work is highlighted here.

Research Projects

Generative Vision for Video Synthesis: Developing user-intuitive controls for generative video models to enable interactive and personalized content creation.
Bias Mitigation in Vision Models: Investigating strategies to mitigate bias in generative models while preserving their generalization capabilities.
Adaptation of Large Models: Adapting large-scale vision and language models to solve personalized tasks efficiently using limited data.

Publications

	TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility Saman Motamed, Minghao Chen, Luc Van Gool, Iro Laina arXiv, 2025 code / arxiv A recipe to make video language models better understand physics, and a rigorous benchmark to test VLMs on physics understanding.
	Do generative video models learn physical principles from watching videos? Saman Motamed, Laura Culp, Kevin Swersky, Priyank Jaini, Robert Geirhos WACV, 2026 code / arxiv A benchmark of real videos for testing physics understanding of generative video models.
	Lego: Learning to Disentangle and Invert Concepts Beyond Object Appearance in Text-to-Image Diffusion Models Saman Motamed, Danda Pani Paudel, Luc Van Gool ECCV, 2024 code / arxiv A method for textual inversion of adjectives and verbs in text-to-image diffusion models.
	Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models Saman Motamed, Wouter Van Gansbeke, Luc Van Gool CVPR Generative Models Workshop, 2024 code / arxiv Zero-shot control over object shape, position and movement in text-to-video models via cross-attention maps.
	A Unified and Interpretable Emotion Representation and Expression Generation Reni Paskaleva, Mykyta Holubakha, Andela Ilic, Saman Motamed, Luc Van Gool, Danda Paudel CVPR, 2024 arxiv Fine-grained generation of expressions in conjunction with other textual inputs and offers a new label space for emotions at the same time.
	D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignment Lin Zhang, Linghan Xu, Saman Motamed, Shayok Chakraborty, Fernando De la Torre WACV, 2024 arxiv A Multi-Target Active Domain Adaptation (MT-ADA) framework for image classification.
	Personalized Face Inpainting With Diffusion Models by Parallel Visual Attention Jianjin Xu, Saman Motamed, Praneetha Vaddamanu, Chen Henry Wu, Christian Haene, Jean-Charles Bazin, Fernando De la Torre WACV, 2024 code / arxiv Fast, identity preserving face inpainting with diffusion models.
	PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpainting Saman Motamed, Jianjin Xu, Chen Henry Wu, Fernando De la Torre ICCV, 2023 ICCV / code / arxiv A tuning method for personalizing inpainting of the face and preserving the identity of a subject.
	Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models Chen Henry Wu, Saman Motamed, Shaunak Srivastava, Fernando De La Torre NeurIPS, 2022 NeurIPS / code / arxiv A framework for defining control over latent-based generative models.

Talks

Invited talks and presentations.

Dec 16, 2025	Improving VLM's understanding of physically implausible scenes. Invited Talk • Vector Institute, Toronto Invited by Dr. Babak Taati • Journal Club
Jan 30, 2025	How to benchmark video generative models for their physics understanding? Invited Talk • Stability AI Reading Group Invited by Rahim Entezari

Somewhat related to computer vision and content creation, I enjoy film photography on 35 mm and medium format film. You can view some of my photos below.

❮ ❯

Feel free to steal this website's source code