Tootfinder

ALICE: An Interpretable Neural Architecture for Generalization in Substitution Ciphers
Jeff Shen, Lindsay Smith
https://arxiv.org/abs/2509.07282 https://ar…

ALICE: An Interpretable Neural Architecture for Generalization in Substitution Ciphers
We present cryptogram solving as an ideal testbed for studying neural network generalization in combinatorially complex domains. In this task, models must decrypt text encoded with substitution ciphers, choosing from 26! possible mappings without explicit access to the cipher. We develop ALICE (an Architecture for Learning Interpretable Cryptogram dEcipherment): a simple encoder-only Transformer that sets a new state-of-the-art for both accuracy and speed on this decryption problem. Surprisingl…

End-to-End Efficiency in Keyword Spotting: A System-Level Approach for Embedded Microcontrollers
Pietro Bartoli, Tommaso Bondini, Christian Veronesi, Andrea Giudici, Niccol\`o Antonello, Franco Zappa
https://arxiv.org/abs/2509.07051

End-to-End Efficiency in Keyword Spotting: A System-Level Approach for Embedded Microcontrollers
Keyword spotting (KWS) is a key enabling technology for hands-free interaction in embedded and IoT devices, where stringent memory and energy constraints challenge the deployment of AI-enabeld devices. In this work, we systematically evaluate and compare several state-of-the-art lightweight neural network architectures, including DS-CNN, LiCoNet, and TENet, alongside our proposed Typman-KWS (TKWS) architecture built upon MobileNet, specifically designed for efficient KWS on microcontroller unit…

Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data
Anastasis Kratsios, Tin Sum Cheng, Daniel Roy
https://arxiv.org/abs/2509.00924

Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data
At its core, machine learning seeks to train models that reliably generalize beyond noisy observations; however, the theoretical vacuum in which state-of-the-art universal approximation theorems (UATs) operate isolates them from this goal, as they assume noiseless data and allow network parameters to be chosen freely, independent of algorithmic realism. This paper bridges that gap by introducing an architecture-specific randomized training algorithm that constructs a uniform approximator from $…

Optimizing Edge Gaming Slices through an Enhanced User Plane Function and Analytics in Beyond-5G Networks
Bruno Marques da Silva, Larissa Ferreira Rodrigues Moreira, Fl\'avio de Oliveira Silva, Rodrigo Moreira
https://arxiv.org/abs/2507.17843

Optimizing Edge Gaming Slices through an Enhanced User Plane Function and Analytics in Beyond-5G Networks
The latest generation of games and pervasive communication technologies poses challenges in service management and Service-Level Agreement compliance for mobile users. State-of-the-art edge-gaming techniques enhance throughput, reduce latency, and leverage cloud computing. However, further development of core functions such as the User Plane Function (UPF) is needed for non-intrusive user latency measurement. This paper proposes a closed-loop architecture integrating the Network Data Analytics …

Binaural Speech Enhancement Using Complex Convolutional Recurrent Networks
Vikas Tokala, Eric Grinstein, Mike Brookes, Simon Doclo, Jesper Jensen, Patrick A. Naylor
https://arxiv.org/abs/2507.20023

Binaural Speech Enhancement Using Complex Convolutional Recurrent Networks
From hearing aids to augmented and virtual reality devices, binaural speech enhancement algorithms have been established as state-of-the-art techniques to improve speech intelligibility and listening comfort. In this paper, we present an end-to-end binaural speech enhancement method using a complex recurrent convolutional network with an encoder-decoder architecture and a complex LSTM recurrent block placed between the encoder and decoder. A loss function that focuses on the preservation of spa…

Uncertainty-Aware Tabular Prediction: Evaluating VBLL-Enhanced TabPFN in Safety-Critical Medical Data
Madhushan Ramalingam
https://arxiv.org/abs/2509.10048 https://

Uncertainty-Aware Tabular Prediction: Evaluating VBLL-Enhanced TabPFN in Safety-Critical Medical Data
Predictive models are being increasingly used across a wide range of domains, including safety-critical applications such as medical diagnosis and criminal justice. Reliable uncertainty estimation is a crucial task in such settings. Tabular Prior-data Fitted Network (TabPFN) is a recently proposed machine learning foundation model for tabular dataset, which uses a generative transformer architecture. Variational Bayesian Last Layers (VBLL) is a state-of-the-art lightweight variational formulati…

A Lightweight Fourier-based Network for Binaural Speech Enhancement with Spatial Cue Preservation
Xikun Lu, Yujian Ma, Xianquan Jiang, Xuelong Wang, Jinqiu Sang
https://arxiv.org/abs/2509.14076

A Lightweight Fourier-based Network for Binaural Speech Enhancement with Spatial Cue Preservation
Binaural speech enhancement faces a severe trade-off challenge, where state-of-the-art performance is achieved by computationally intensive architectures, while lightweight solutions often come at the cost of significant performance degradation. To bridge this gap, we propose the Global Adaptive Fourier Network (GAF-Net), a lightweight deep complex network that aims to establish a balance between performance and computational efficiency. The GAF-Net architecture consists of three components. Fi…