Generative diffusion models are well-suited for probabilistic precipitation nowcasting, but existing approaches often rely on separately trained compression or deterministic forecasting components and remain costly at inference due to iterative denoising. We introduce Just Weather Scoring (JWS), a single-stage, end-to-...
Jannik Wiese, Johannes Schusterbauer, Tommaso Martorella et al.· 0 citations
A stochastic few-step generator whose FID does not degrade as the sampling budget grows from 4 to 50 NFE, and the same recipe transfers to text-to-image generation.
Tommaso Martorella, Alexandre Galashov, F. Krause et al.· arXiv.org· 1 citation
The Logit Refiner is introduced, a lightweight autoregressive module that restores intra-scale dependencies by sequentially sampling tokens conditioned on frozen backbone features and generalizes to text-to-image generation, confirming that the mean-field bottleneck persists across VAR variants and is effectively allev...
Meimingwei Li, S. Baumann, F. Krause et al.· 0 citations
This work introduces a promptable localized motion representation that produces persistent embeddings for user-specified regions defined by spatial masks that improves controllability and outperforms global representations localized through cropping or post-hoc masking.
Frank Fundel, Malek Ben Alaya, Thomas Ressler-Antal et al.· 0 citations
A novel notion of concept-wise mutual information is introduced and large, concept-dependent differences between individual layers are found, demonstrating that the generation of specific structures is localized in distinct parts of the network.
Nikolai Röhrich, Isabell Hans, F. Krause et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.