PhD candidate at @ait_eth and Disney Research
Switzerland
Joined November 2018
- Tweets207
- Following118
- Followers163
- Likes147
Pinned Tweet
Excited to present two papers at #ICLR2025 in Singapore 🇸🇬! If you are attending, please drop by our posters to talk about diffusion models 🔥
Details in the thread 🧵👇
Morteza Sadat retweeted
Please help spread the word!
We’re hiring Research Scientists and Research Interns at NVIDIA Research to work on some of the most exciting problems in generative AI:
🌎 World Models & Video Diffusion
🧠 Diffusion Language Models
🧬 Biomolecule Design
If your research aligns with any of these areas, please apply directly through the links below.
Open positions + application links:
research.nvidia.com/labs/gen…
🚀🚀 I will present our latest work " HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models" next week at ICLR 2026 🇧🇷 🎉 If you’re attending, I’d love to connect and chat!
Morteza Sadat retweeted
Efficient Distillation of Classifier-Free Guidance using Adapters
Cristian Perez Jensen, Seyedmorteza Sadat.
Action editor: Chang Xu.
openreview.net/forum?id=uMz8…
#distillation #guided #models
Happy to be selected as an Outstanding Reviewer for ICCV and NeurIPS! 🙌🎉🎈
Special thanks to the ACs for acknowledging this! 🙂
[1/8]🚨📢Introducing "HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models"; A tweak to diffusion sampling that makes images sharper, more coherent, and more realistic, especially with fewer steps or low guidance.
[7/8] Finally, we show that HiGS is compatible with a wide range of diffusion models and samplers (including distilled variants), and can be integrated into existing pipelines without retraining or additional sampling overhead.
[8/8] Please check out the paper for more details and experiments, as well as the PyTorch pseudocode of the method.:
huggingface.co/papers/2509.2…
I'd like to thank all my colleagues who made this project possible.
Morteza Sadat retweeted
Congrats! Our work on TPG (Token Perturbation Guidance (with @rajabi2001 @SoroushMehraban @Msadat97) was also accepted to #NeurIPS2025. Let's connect and exchange ideas at @NeurIPSConf.
teapawt.net/rajabi2001/status/1938…
[1/7]⚡️Check out our recent work — "Token Perturbation Guidance for Diffusion Models"
A simple yet effective method based on token shuffling for extending the benefits of CFG to broader settings, including unconditional generation.
arXiv: arxiv.org/abs/2506.10036
Morteza Sadat retweeted
Excited to share minHiWave, my reimplementation of the HiWave paper! Clean code, minimal setup, and ready to run. Check it out: github.com/laihongphuc/minHi…
Morteza Sadat retweeted
[LG] Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales
S Sadat, T Vontobel, F Salehi, R M. Weber [ETH Zürich & DisneyResearch|Studios] (2025)
arxiv.org/abs/2506.19713
Pretty exciting to see two community implementations of our Frequency-Decoupled Guidance (FDG) in ComfyUI! 🚀
Huge thanks to the contributors:
🔗 github.com/sdtana/ComfyUI-FD…
🔗 github.com/asagi4/ComfyUI-FD…
Note: I haven’t personally tested the code for correctness.
Please check out our discussion here if you would like to see more information regarding the paper.
teapawt.net/Msadat97/status/193790…
Morteza Sadat retweeted
Preprint of today: Sadat et al., "Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales" -- arxiv.org/abs/2506.19713
Classifier Free Guidance affects generation differently at different frequencies -- set it to low for low frequency, and high for high!
Morteza Sadat retweeted
Preprint of today: Vontobel et al., "HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling" -- arxiv.org/abs/2506.20452
This one also uses wavelets and frequency-dependent guidance. Generate->Invert->Add high-freq details for each part.
