Tootfinder

Inference Time Debiasing Concepts in Diffusion Models
Lucas S. Kupssinsk\"u, Marco N. Bochernitsan, Jordan Kopper, Ot\'avio Parraga, Rodrigo C. Barros
https://arxiv.org/abs/2508.14933

Inference Time Debiasing Concepts in Diffusion Models
We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based image generation model. DeCoDi changes the diffusion process to avoid latent dimension regions of biased concepts. While most deep learning debiasing methods require complex or compute-intensive interventions, our method is designed to change only the inferen…

Going with the Flow: Solving for Symmetry-Driven PDE dynamics with Physics-informed Neural Networks
Michail Kavousanakis, Gianluca Fabiani, Anastasia Georgiou, Constantinos Siettos, Panagiotis Kevrekidis, Ioannis Kevrekidis
https://arxiv.org/abs/2509.15963

Going with the Flow: Solving for Symmetry-Driven PDE dynamics with Physics-informed Neural Networks
In the past, we have presented a systematic computational framework for analyzing self-similar and traveling wave dynamics in nonlinear partial differential equations (PDEs) by dynamically factoring out continuous symmetries such as translation and scaling. This is achieved through the use of time-dependent transformations -- what can be viewed as dynamic pinning conditions -- that render the symmetry-invariant solution stationary or slowly varying in rescaled coordinates. The transformation pr…

🇺🇦 #NowPlaying on #KEXP's #DriveTime
Guru feat. Angie Stone:
🎵 Keep Your Worries
#Guru #AngieStone
https://djsugai.bandcamp.com/track/guru-ft-angie-stone-keep-your-worries
https://open.spotify.com/track/2iYM4CGkoTfsLw9MI5K1AC
🎶 show playlist 👇
https://open.spotify.com/playlist/2KW4FxNKVGpVTgIJYolnNY
🎶 KEXP playlist 👇
https://open.spotify.com/playlist/6VNALrOa3gWbk794YuIrwg