Tootfinder

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
Muhammad Shakeel, Yui Sudo, Yifan Peng, Chyi-Jiunn Lin, Shinji Watanabe
https://arxiv.org/abs/2508.20474 htt…

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
This paper presents a unified multi-speaker encoder (UME), a novel architecture that jointly learns representations for speaker diarization (SD), speech separation (SS), and multi-speaker automatic speech recognition (ASR) tasks using a shared speech foundational encoder. We leverage the hidden representations from multiple layers of UME as a residual weighted-sum encoding (RWSE) to effectively use information from different semantic levels, contributing to bottom-up alignment between tasks. Th…

Study of higher-order interactions in unweighted, undirected networks using persistent homology
Udit Raj, Slobodan Maleti\'c, Sudeepto Bhattacharya
https://arxiv.org/abs/2506.19448

Study of higher-order interactions in unweighted, undirected networks using persistent homology
Persistent homology has been studied to better understand the structural properties and topology features of weighted networks. It can reveal hidden layers of information about the higher-order structures formed by non-pairwise interactions in a network. Studying of higher-order interactions (HoIs) of a system provides a more comprehensive understanding of the complex system; moreover, it is a more precise depiction of the system as many complex systems, such as ecological systems and biologica…

Rank Inspired Neural Network for solving linear partial differential equations
Wentao Peng, Yunqing Huang, Nianyu Yi
https://arxiv.org/abs/2506.17654 https…

Rank Inspired Neural Network for solving linear partial differential equations
This paper proposes a rank inspired neural network (RINN) to tackle the initialization sensitivity issue of physics informed extreme learning machines (PIELM) when numerically solving partial differential equations (PDEs). Unlike PIELM which randomly initializes the parameters of its hidden layers, RINN incorporates a preconditioning stage. In this stage, covariance-driven regularization is employed to optimize the orthogonality of the basis functions generated by the last hidden layer. The key…

Topological Uncertainty for Anomaly Detection in the Neural-network EoS Inference with Neutron Star Data
Kenji Fukushima, Syo Kamata
https://arxiv.org/abs/2508.19683 https://

Topological Uncertainty for Anomaly Detection in the Neural-network EoS Inference with Neutron Star Data
We study the performance of the Topological Uncertainty (TU) constructed with a trained feedforward neural network (FNN) for Anomaly Detection. Generally, meaningful information can be stored in the hidden layers of the trained FNN, and the TU implementation is one tractable recipe to extract buried information by means of the Topological Data Analysis. We explicate the concept of the TU and the numerical procedures. Then, for a concrete demonstration of the performance test, we employ the Neut…

Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising
Jin Ye, Jingran Wang, Fengchao Xiong, Jingzhou Chen, Yuntao Qian
https://arxiv.org/abs/2508.15553 …

Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising
Hyperspectral images (HSIs) play a crucial role in remote sensing but are often degraded by complex noise patterns. Ensuring the physical property of the denoised HSIs is vital for robust HSI denoising, giving the rise of deep unfolding-based methods. However, these methods map the optimization of a physical model to a learnable network with a predefined depth, which lacks convergence guarantees. In contrast, Deep Equilibrium (DEQ) models treat the hidden layers of deep networks as the solution…

On the Effect of Uncertainty on Layer-wise Inference Dynamics
Sunwoo Kim, Haneul Yoo, Alice Oh
https://arxiv.org/abs/2507.06722 https://

On the Effect of Uncertainty on Layer-wise Inference Dynamics
Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations. While several studies have shown that models encode uncertainty in their hidden states, it is underexplored how this affects the way they process such hidden states. In this work, we demonstrate that the dynamics of output token probabilities across layers for certain and uncertain outputs are largely aligned, revealing that uncerta…

Deciphering hidden layers images through terahertz spectral fingerprints
Candida Moffa, Daniele Francescone, Alessandro Curcio, Anna Candida Felici, Marco Bellaveglia, Luca Piersanti, Mauro Migliorati, Massimo Petrarca
https://arxiv.org/abs/2505.23965

Deciphering hidden layers images through terahertz spectral fingerprints
Terahertz radiation enables non destructive, depthresolved analysis of layered artworks. This study demonstrates THz multispectral imaging ability to reveal concealed text beneath mockup of pictorial layers, reconstructing hidden narratives at varying depths through frequency domain analysis.Simultaneously, it maps pigment composition, providing valuable chemical information. Showcasing the power to penetrate and decipher stratified materials, this work establishes THz multispectral imaging as …

Unveiling Usability Challenges in Web Privacy Controls
Rahat Masood, Sunday Oyinlola Ogundoyin, Muhammad Ikram, Alex Ye
https://arxiv.org/abs/2507.11908 ht…

Unveiling Usability Challenges in Web Privacy Controls
With the increasing concerns around privacy and the enforcement of data privacy laws, many websites now provide users with privacy controls. However, locating these controls can be challenging, as they are frequently hidden within multiple settings and layers. Moreover, the lack of standardization means these controls can vary widely across services. The technical or confusing terminology used to describe these controls further complicates users' ability to understand and use them effectively. …

Regional, Lattice and Logical Representations of Neural Networks
Sandro Preto (Federal University of ABC, Brazil), Marcelo Finger (University of Sao Paulo, Brazil)
https://arxiv.org/abs/2506.05834

Regional, Lattice and Logical Representations of Neural Networks
A possible path to the interpretability of neural networks is to (approximately) represent them in the regional format of piecewise linear functions, where regions of inputs are associated to linear functions computing the network outputs. We present an algorithm for the translation of feedforward neural networks with ReLU activation functions in hidden layers and truncated identity activation functions in the output layer. We also empirically investigate the complexity of regional representati…

Uncovering Synergistic Educational Injustices of COVID-19 and AI
Ahmad Banyasady (Malayer university)
https://arxiv.org/abs/2507.03095 https://

Uncovering Synergistic Educational Injustices of COVID-19 and AI
Grounded in critical realism and using narrative inquiry, this article explores this article explores the long-term consequences of the COVID-19 pandemic and the rapid proliferation of artificial intelligence within higher education. Through the analysis of student narratives collected in Iranian university settings, the study reveals that learning experiences during and after the pandemic, coupled with unprepared exposure to AI tools, have generated hidden yet impactful layers of educational i…

TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Xiaoxing Mo, Yuxuan Cheng, Nan Sun, Leo Yu Zhang, Wei Luo, Shang Gao
https://arxiv.org/abs/2506.10722

TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Deep Neural Networks (DNNs) are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics (TED) has recently emerged as a powerful tool for detecting backdoor attacks in DNNs. However, TED can be vulnerable to backdoor attacks that adaptively distort topological representation distributions across network layers. To address this limitation, we propose TED-LaST (Topological Evolution Dynamics agai…

This https://arxiv.org/abs/2403.05809 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Shallow ReLU neural networks and finite elements
We point out that (continuous or discontinuous) piecewise linear functions on a convex polytope mesh can be represented by two-hidden-layer ReLU neural networks in a weak sense. In addition, the numbers of neurons of the two hidden layers required to weakly represent are accurately given based on the numbers of polytopes and hyperplanes involved in this mesh. The results naturally hold for constant and linear finite element functions. Such weak representation establishes a bridge between shallo…

It’s already 25°C and I am dripping with sweat… but a slight modification had to be completed! Made a shelf in the main #poolpond area to hold a milk crate, which will hold one of the pumps.
I decided it was critical to have circulation from the bottom of the pool including taking water from the bottom to send to the filter. But since the main pump area is in the intake bay/skimmer I would have had to bring a pipe up and over the wall and down into pool. (The pumps must be submerged in at least 6” of water at all times)
This would be inefficient and potentially have air lock problems… so I pulled back the three layers of liner and cloth and excavated a little nook in the already semi hidden back corner.
This will have to do. :) the sun was already coming over the house. The rubber liner gets very hot 🥵. Glad it didn’t take too long.
There will be a rock or some sort of wall below and in front of the crate to further support and hide it.
Oh, and now that the liner and stuff is all back, the 🐜 ants can go back to their regularly scheduled ant-ing.
#diy #backyardpond #hot #ants #gardening #homeimprovement #portalberni