Tootfinder

Learning User Preferences for Image Generation Model
Wenyi Mo, Ying Ba, Tianyu Zhang, Yalong Bai, Biye Li
https://arxiv.org/abs/2508.08220 https://arxiv.or…

Learning User Preferences for Image Generation Model
User preference prediction requires a comprehensive and accurate understanding of individual tastes. This includes both surface-level attributes, such as color and style, and deeper content-related aspects, such as themes and composition. However, existing methods typically rely on general human preferences or assume static user profiles, often neglecting individual variability and the dynamic, multifaceted nature of personal taste. To address these limitations, we propose an approach built upo…

Impact of Force Noise on the Visibility of STA-Based Atom Interferometers
Sof\'ia Mart\'inez-Garaot, I. Lizuain, A. Rodriguez-Prieto, J. G. Muga
https://arxiv.org/abs/2509.09369

Impact of Force Noise on the Visibility of STA-Based Atom Interferometers
In a previous work, we designed a compact atom interferometer to measure homogeneous constant forces guiding the arms via shortcuts to adiabatic paths. Within this scheme we drive the atom by moving spin-dependent traps, and design a force $f(t)$ to compensate inertial terms in the moving frame. In this paper we analyze how robust our interferometer is against some realistic noisy deviation from the unperturbed value of the force $f(t)$. The complex overlap of the atom wave functions for each a…

Capsule-ConvKAN: A Hybrid Neural Approach to Medical Image Classification
Laura Pitukov\'a, Peter Sin\v{c}\'ak, L\'aszl\'o J\'ozsef Kov\'acs
https://arxiv.org/abs/2507.06417

Capsule-ConvKAN: A Hybrid Neural Approach to Medical Image Classification
This study conducts a comprehensive comparison of four neural network architectures: Convolutional Neural Network, Capsule Network, Convolutional Kolmogorov--Arnold Network, and the newly proposed Capsule--Convolutional Kolmogorov--Arnold Network. The proposed Capsule-ConvKAN architecture combines the dynamic routing and spatial hierarchy capabilities of Capsule Network with the flexible and interpretable function approximation of Convolutional Kolmogorov--Arnold Networks. This novel hybrid mod…

Graphene-Gold THz Metasurfaces with Tailored Resonant Structure for Enhanced Nonlinear Response
Anna Theodosi, Isaac Appiah Otoo, Anastasios D. Koulouklidis, Nikolaos Matthaiakakis, George Kakarantzas, Petri Mustonen, Harri Lipsanen, Georgy Fedorov, Ioannis Liontos, Stelios Tzortzakis, Polina Kuzhir, Maria Kafesaki, Odysseas Tsilipakos
https://

Graphene-Gold THz Metasurfaces with Tailored Resonant Structure for Enhanced Nonlinear Response
Graphene's exceptional nonlinear optical properties combined with resonant photonic structures offer a promising pathway for efficient nonlinear applications at terahertz (THz) frequencies. In this work, we propose and demonstrate a fabrication-friendly hybrid nonlinear metasurface composed of gold patches integrated with uniform graphene, circumventing the need for complex graphene patterning. The structure supports strong localized resonances that enhance nonlinear interactions. By exploiting…

The new TV came in and it has been beat to absolute hell. The TV itself is now slightly out-of-square, the front bezel was shattered (the top bit is kinda just stuck there as is the left-hand side), and the outer shell is pretty bent.
However, the tube is perfect and the TV is 100% functional (composite and S-video) which is absolute insanity. I'm not sure how I want to proceed on this one.

If you are confused about the date of the birth of the web:
https://w3c.social/@w3c/114981709192442504
It’s only because it’s confusing.
12 March 1989 is when TimBL submitted the proposal:

World Wide Web Consortium (@w3c@w3c.social)
Attached: 1 image Today is the anniversary of the release of the web to the world to the world, in 1991, by @timbl when he said "Try it" Billions have taken up his call to use the web. W3C, as a steward of this initial gift since 1994, is realizing our vision of making the web work, for everyone – a web designed for the good of its users, that is safe and secure. https://www.w3.org/blog/2025/vision-for-w3c-to-reach-durable-and-sustainable-success/

from my link log —
In praise of grobi for auto-configuring X11 monitors.
https://michael.stapelberg.ch/posts/2025-05-10-grobi-x11-monitor-autoconfig/
saved 2025-05-10

Low-Rank Regularized Convex-Non-Convex Problems for Image Segmentation or Completion
Mohamed El Guide, Anas El Hachimi, Khalide Jbilou, Lothar Reichel
https://arxiv.org/abs/2508.21765

Low-Rank Regularized Convex-Non-Convex Problems for Image Segmentation or Completion
This work proposes a novel convex-non-convex formulation of the image segmentation and the image completion problems. The proposed approach is based on the minimization of a functional involving two distinct regularization terms: one promotes low-rank structure in the solution, while the other one enforces smoothness. To solve the resulting optimization problem, we employ the alternating direction method of multipliers (ADMM). A detailed convergence analysis of the algorithm is provided, and th…

MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation
Yuan Zhao, Liu Lin
https://arxiv.org/abs/2509.04126 https://arxiv.org/p…

MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation
Text-to-image diffusion models have achieved remarkable image quality, but they still struggle with complex, multiele ment prompts, and limited stylistic diversity. To address these limitations, we propose a Multi-Expert Planning and Gen eration Framework (MEPG) that synergistically integrates position- and style-aware large language models (LLMs) with spatial-semantic expert modules. The framework comprises two core components: (1) a Position-Style-Aware (PSA) module that utilizes a supervised…

Beyond Pixels: Medical Image Quality Assessment with Implicit Neural Representations
Caner \"Ozer, Patryk Rygiel, Bram de Wilde, \.Ilkay \"Oks\"uz, Jelmer M. Wolterink
https://arxiv.org/abs/2508.05168

Beyond Pixels: Medical Image Quality Assessment with Implicit Neural Representations
Artifacts pose a significant challenge in medical imaging, impacting diagnostic accuracy and downstream analysis. While image-based approaches for detecting artifacts can be effective, they often rely on preprocessing methods that can lead to information loss and high-memory-demand medical images, thereby limiting the scalability of classification models. In this work, we propose the use of implicit neural representations (INRs) for image quality assessment. INRs provide a compact and continuou…