Sotabase

Career

· PhD Student, Advanced Interactive Technologies lab, ETH Zürich & DisneyResearch|Studios2022–
· MS in Computer Science, ETH Zürich2020–2022
· B.Sc. in Electrical Engineering, Sharif University of Technology2015–2019

Publications (11)

CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
International Conference on Learning Representations · 2023
95
cited
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
International Conference on Learning Representations · 2024
52
cited
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
International Conference on Learning Representations · 2024
37
cited
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Neural Information Processing Systems · 2024
18
cited
Factorized Motion Diffusion for Precise and Character-Agnostic Motion Inbetweening
Motion in Games · 2024
8
cited
Token Perturbation Guidance for Diffusion Models
arXiv.org · 2025
6
cited
Efficient Distillation of Classifier-Free Guidance using Adapters
Trans. Mach. Learn. Res. · 2025
3
cited
Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales
arXiv.org · 2025
3
cited
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia · 2025
3
cited
HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models
arXiv.org · 2025
Regressor-Guided Generative Image Editing Balances User Emotions to Reduce Time Spent Online
2025
Sotabase
Seyedmorteza Sadat | Researcher Profile | Sotabase | Sotabase