Morteza Sadat

PhD candidate at @ait_eth and Disney Research

[Morteza Sadat @Msadat97]

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 @Msadat97]

🚀🚀 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 @Msadat97]

[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.

[Accepted papers at TMLR @TmlrPub]

Efficient Distillation of Classifier-Free Guidance using Adapters

Cristian Perez Jensen, Seyedmorteza Sadat.

Action editor: Chang Xu.

https://t.co/bp1Fk4GQ7M

#distillation #guided #models

[Morteza Sadat @Msadat97]

@dogacel0 Pretty annoying to see that 30% of reviews are ai-generated

[Morteza Sadat @Msadat97]

@youjiaxuan One of our reviewers asked for a combinatorial grid search over all ablation parameters instead of changing only one at a time :))

[Morteza Sadat @Msadat97]

@CSProfKGD

[Morteza Sadat @Msadat97]

Happy to be selected as an Outstanding Reviewer for ICCV and NeurIPS! 🙌🎉🎈

Special thanks to the ACs for acknowledging this! 🙂

[Morteza Sadat @Msadat97]

[8/8] Please check out the paper for more details and experiments, as well as the PyTorch pseudocode of the method.:
https://t.co/Ym2lBe9LGa

I'd like to thank all my colleagues who made this project possible.

[Morteza Sadat @Msadat97]

[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.

[Morteza Sadat @Msadat97]

[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.

[Babak Taati @Babak_Taati]

@donghoon_ahn @NeurIPSConf 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.

https://t.co/Pui2iUezxv

[Morteza Sadat @Msadat97]

@jbhuang0604 @CSProfKGD One of ours said that your method shouldn't be accepted because it has two hyperparameters.

[Morteza Sadat @Msadat97]

@latifian_m It might be necessary given the scale of the conference. Almost 60/70 percent of reviewers haven't replied anything to the rebuttals among my papers (both as an author and as a reviewer)

[Morteza Sadat @Msadat97]

@roydanroy One of ours actually said the method is unreasonable because it's simple and straightforward :))

[Puneesh Deora @puneeshdeora]

NeurIPS releasing reviews one by one.

[Morteza Sadat @Msadat97]

@Phc14097930 Cool! Thanks a lot. Let me know if you have any questions.

[Morteza Sadat @Msadat97]

Thanks, AK, for sharing our work!

Also, feel free to check out our related paper, where we explore how frequency analysis can generally enhance image generation in diffusion models: https://t.co/m1P2eMjVFb

[AK @_akhaliq]

HiWave

Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling