Tootfinder

Prediction-Powered Communication with Distortion Guarantees
Matteo Zecchin, Unnikrishnan Kunnath Ganesan, Giuseppe Durisi, Petar Popovski, Osvaldo Simeone
https://arxiv.org/abs/2509.24373

Prediction-Powered Communication with Distortion Guarantees
The development of 6G wireless systems is taking place alongside the development of increasingly intelligent wireless devices and network nodes. The changing technological landscape is motivating a rethinking of classical Shannon information theory that emphasizes semantic and task-oriented paradigms. In this paper, we study a prediction-powered communication setting, in which devices, equipped with artificial intelligence (AI)-based predictors, communicate under zero-delay constraints with str…

A multiscale analysis of mean-field transformers in the moderate interaction regime
Giuseppe Bruno, Federico Pasqualotto, Andrea Agazzi
https://arxiv.org/abs/2509.25040 https://…

A multiscale analysis of mean-field transformers in the moderate interaction regime
In this paper, we study the evolution of tokens through the depth of encoder-only transformer models at inference time by modeling them as a system of particles interacting in a mean-field way and studying the corresponding dynamics. More specifically, we consider this problem in the moderate interaction regime, where the number $N$ of tokens is large and the inverse temperature parameter $β$ of the model scales together with $N$. In this regime, the dynamics of the system displays a multiscal…

From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation
Abdelhakim Benechehab, Gabriel Singer, Corentin L\'eger, Youssef Attia El Hili, Giuseppe Paolo, Albert Thomas, Maurizio Filippone, Bal\'azs K\'egl
https://arxiv.org/abs/2510.07624

From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation
Generative models form the backbone of modern machine learning, underpinning state-of-the-art systems in text, vision, and multimodal applications. While Maximum Likelihood Estimation has traditionally served as the dominant training paradigm, recent work have highlighted its limitations, particularly in generalization and susceptibility to catastrophic forgetting compared to Reinforcement Learning techniques, such as Policy Gradient methods. However, these approaches depend on explicit reward …

In-pixel integration of signal processing and AI/ML based data filtering for particle tracking detectors
Benjamin Parpillon, Anthony Badea, Danush Shekar, Christian Gingu, Giuseppe Di Guglielmo, Tom Deline, Adam Quinn, Michele Ronchi, Benjamin Weiss, Jennet Dickinson, Jieun Yoo, Corrinne Mills, Daniel Abadjiev, Eric You, Mira Littmann, Karri DiPetrillo, Arghya Ranjan Das, Mia Liu, David Jiang, Mark S. Neubauer, Morris Swartz, Petar Maksimovic, Alice Bean, Chinar Syal, Doug Berry, Nhan …

In-pixel integration of signal processing and AI/ML based data filtering for particle tracking detectors
We present the first physical realization of in-pixel signal processing with integrated AI-based data filtering for particle tracking detectors. Building on prior work that demonstrated a physics-motivated edge-AI algorithm suitable for ASIC implementation, this work marks a significant milestone toward intelligent silicon trackers. Our prototype readout chip performs real-time data reduction at the sensor level while meeting stringent requirements on power, area, and latency. The chip is taped…

2 shots, neither on target… one blocked, one over the bar. For all the talk about defensive woes, the offense isn’t producing anything. Salah has one brilliant pass and not much else. Gakpo is disconnected. And Isak hasn’t been fed much at all.
Szoboszlai has been running absolutely full tilt everywhere, trying to carry this sluggish team forward. But, unfortunately, it pulls the shape apart. Gravenberch has been solid. Mac Allister is not himself, but better than past games.

On actions and split extensions in varieties of hoops: the case of strong section
Manuel Mancini, Giuseppe Metere, Federica Piazza
https://arxiv.org/abs/2510.06886 https://

On actions and split extensions in varieties of hoops: the case of strong section
The aim of this article is to investigate internal actions and split extensions in the variety of hoops. We provide a characterization of split extensions with strong section in terms of strong external actions. Beyond the general setting of hoops, the study is extended to the subvarieties of basic hoops, Wajsberg hoops, Gödel hoops and product hoops. Within the setting of basic hoops and their bounded counterparts, BL-algebras, the double negation yields a significant example of split extensi…

Reservoir computing based predictive reduced order model for steel grade intermixing in an industrial continuous casting tundish
Harshith Gowrachari, Mattia Giuseppe Barra, Giovanni Stabile, Gianluca Bazzaro, Gianluigi Rozza
https://arxiv.org/abs/2509.26293

Reservoir computing based predictive reduced order model for steel grade intermixing in an industrial continuous casting tundish
Continuous casting is a widely adopted process in the steel industry, where maintaining high steel quality is paramount. Efficient prediction of grade intermixing during ladle changeover operations is critical for maintaining steel quality and minimizing material losses in the continuous casting process. Among various factors influencing grade intermixing, operating parameters play a significant role, in addition to tundish geometry and flow control devices. In this study, three-dimensional, tr…

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework
Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara, Nicola Messina, Giuseppe Amato, Fabrizio Falchi
https://arxiv.org/abs/2510.02898 …

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework
Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption an image, they proceed by textually decoding a text-aligned image feature, but they limit their scope to global representations and whole-image captions. We present \frameworkName{}, a unified framework for zero-shot captioning that shifts from an image-centric to a patch-centric paradigm, enabling the captioning of a…

Energy distance and evolution problems: a promising tool for kinetic equations
Gennaro Auricchio, Giuseppe Toscani
https://arxiv.org/abs/2510.09123 https://

Energy distance and evolution problems: a promising tool for kinetic equations
We study the rate of convergence to equilibrium of the solutions to Fokker-Planck type equations with linear drift by means of Cramér and Energy distances, which have been recently widely used in problems related to AI, in particular for tasks related to machine learning. In all cases in which the Fokker-Planck type equations can be treated through these distances, it is shown that the rate of decay is improved with respect to known results which are based on the decay of relative entropy.

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
David Debot, Giuseppe Marra
https://arxiv.org/abs/2510.05670 https://

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts information flow and often results in reduced predictive accuracy. Concept Sidechannel Models (CSMs) address this limitation by introducing a sidechannel that bypasses the bottleneck and carry additional task-relevant information. While this improves accuracy, it …