Seyedmorteza Sadat
Ph.D. student at DisneyResearch|Studios & ETH Zurich
Hi there! I am a joint Ph.D. student between DisneyResearch|Studios and ETH Zurich supervised by Prof. Otmar Hilliges, Prof. Thomas Hofmann, and Dr. Romann Weber.
I specialize in diffusion models for image and video generation. My research focuses on developing novel sampling and guidance techniques to improve the quality, diversity, and efficiency of diffusion models. More broadly, I am interested in how diffusion models can be trained and tuned for visual content creation, as well as their role in creative applications and world modeling.
Prior to my Ph.D., I obtained my master’s degree in Computer Science from ETH Zurich and my bachelor’s degree in Electrical Engineering from Sharif University of Technology.
news
| Dec 05, 2022 | I started my Ph.D. at DisneyResarch|Studios and ETH Zurich. |
|---|
selected publications
- ICLR 2026HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion ModelsIn The Fourteenth International Conference on Learning Representations, 2026
- arXivGuidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales2025
- TMLREfficient Distillation of Classifier-Free Guidance using AdaptersTransactions on Machine Learning Research, 2025
- NeurIPS 2025Token Perturbation Guidance for Diffusion ModelsIn The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
- SIGGRAPH Asia 2025HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling2025
- ICLR 2025Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion ModelsIn The Thirteenth International Conference on Learning Representations, 2025
- ICLR 2025No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion ModelsIn The Thirteenth International Conference on Learning Representations, 2025
- NeurIPS 2024LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion ModelsIn The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
- ICLR 2024CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed SamplingIn The Twelfth International Conference on Learning Representations, 2024