collaborators

9 papers

cs.LG2026

The Score-Difference Flow for Implicit Generative Modeling

Romann M. Weber

Implicit generative modeling (IGM) aims to produce samples of synthetic data matching the characteristics of a target data distribution. Recent work (e.g. score-matching networks,…

cs.CV2026

Reviving ConvNeXt for Efficient Convolutional Diffusion Models

Taesung Kwon, Lorenzo Bianchi, Lennart Wittke +5

Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter effic…

cs.CV2025

HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models

Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber

While diffusion models have made remarkable progress in image generation, their outputs can still appear unrealistic and lack fine details, especially when using fewer number of ne…

cs.CV2025

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

Tobias Vontobel, Seyedmorteza Sadat, Farnood Salehi +1

Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resoluti…

cs.LG2025

Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales

Seyedmorteza Sadat, Tobias Vontobel, Farnood Salehi +1

Classifier-free guidance (CFG) has become an essential component of modern conditional diffusion models. Although highly effective in practice, the underlying mechanisms by which C…

cs.LG2025

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber

Classifier-free guidance (CFG) is crucial for improving both generation quality and alignment between the input condition and final output in diffusion models. While a high guidanc…