1.4k citations · 5.3k across the 49 of their papers we have counts for
49 papers
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo +3
Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermedia…
Efficient Reasoning on the Edge
Yelysei Bondarenko, Thomas Hehn, Rob Hesselink +15
Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large…
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi
\ac{CoT} prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing ``Budget Forcing'' methods reduce cost via fine-tuning with h…
LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents
Amin Rakhsha, Thomas Hehn, Pietro Mazzaglia +3
Large language models can perform well on many isolated tasks, yet they continue to struggle on multi-turn, long-horizon agentic problems that require skills such as planning, stat…
Fundamental bounds on efficiency-confidence trade-off for transductive conformal prediction
Arash Behboodi, Alvaro H. C. Correia, Fabio Valerio Massoli +1
Transductive conformal prediction addresses the simultaneous prediction for multiple data points. Given a desired confidence level, the objective is to construct a prediction set t…
Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems
Gianluigi Silvestri, Fabio Valerio Massoli, Tribhuvanesh Orekondy +2
A promising way to mitigate the expensive process of obtaining a high-dimensional signal is to acquire a limited number of low-dimensional measurements and solve an under-determine…
Variational Learning ISTA
Fabio Valerio Massoli, Christos Louizos, Arash Behboodi
Compressed sensing combines the power of convex optimization techniques with a sparsity-inducing prior on the signal space to solve an underdetermined system of equations. For many…
Simulating, Fast and Slow: Learning Policies for Black-Box Optimization
Fabio Valerio Massoli, Tim Bakker, Thomas Hehn +2
Simulators are vital in science and engineering, as they faithfully model the influence of design parameters on real-world observations. Optimizing design parameters to minimize a…
An Information Theoretic Perspective on Conformal Prediction
Alvaro H. C. Correia, Fabio Valerio Massoli, Christos Louizos +1
Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probab…
Vision-Assisted Digital Twin Creation for mmWave Beam Management
Maximilian Arnold, Bence Major, Fabio Valerio Massoli +2
In the context of communication networks, digital twin technology provides a means to replicate the radio frequency (RF) propagation environment as well as the system behaviour, al…
Beyond Codebook-Based Analog Beamforming at mmWave: Compressed Sensing and Machine Learning Methods
Hamed Pezeshki, Fabio Valerio Massoli, Arash Behboodi +6
Analog beamforming is the predominant approach for millimeter wave (mmWave) communication given its favorable characteristics for limited-resource devices. In this work, we aim at…
Equivariant Priors for Compressed Sensing with Unknown Orientation
Anna Kuzina, Kumar Pratik, Fabio Valerio Massoli +1
In compressed sensing, the goal is to reconstruct the signal from an underdetermined system of linear measurements. Thus, prior knowledge about the signal of interest and its struc…
A Leap among Quantum Computing and Quantum Neural Networks: A Survey
Fabio Valerio Massoli, Lucia Vadicamo, Giuseppe Amato +1
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development. The ability to harness quantum phenomena to solve comp…
MAFER: a Multi-resolution Approach to Facial Expression Recognition
Fabio Valerio Massoli, Donato Cafarelli, Claudio Gennaro +2
Emotions play a central role in the social life of every human being, and their study, which represents a multidisciplinary subject, embraces a great variety of research fields. Es…
A Multi-resolution Approach to Expression Recognition in the Wild
Fabio Valerio Massoli, Donato Cafarelli, Giuseppe Amato +1
Facial expressions play a fundamental role in human communication. Indeed, they typically reveal the real emotional status of people beyond the spoken language. Moreover, the compr…
Expression Recognition Analysis in the Wild
Donato Cafarelli, Fabio Valerio Massoli, Fabrizio Falchi +2
Facial Expression Recognition(FER) is one of the most important topic in Human-Computer interactions(HCI). In this work we report details and experimental results about a facial ex…
MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
Fabio Valerio Massoli, Fabrizio Falchi, Alperen Kantarci +3
Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly co…
Detection of Face Recognition Adversarial Attacks
Fabio Valerio Massoli, Fabio Carrara, Giuseppe Amato +1
Deep Learning methods have become state-of-the-art for solving tasks such as Face Recognition (FR). Unfortunately, despite their success, it has been pointed out that these learnin…
Cross-Resolution Learning for Face Recognition
Fabio Valerio Massoli, Giuseppe Amato, Fabrizio Falchi
Convolutional Neural Networks have reached extremely high performances on the Face Recognition task. Largely used datasets, such as VGGFace2, focus on gender, pose and age variatio…
Search for Bosonic Super-WIMP Interactions with the XENON100 Experiment
XENON collaboration, E. Aprile, J. Aalbers +118
We present results of searches for vector and pseudo-scalar bosonic super-WIMPs, which are dark matter candidates with masses at the keV-scale, with the XENON100 experiment. XENON1…
Signal Yields of keV Electronic Recoils and Their Discrimination from Nuclear Recoils in Liquid Xenon
E. Aprile, J. Aalbers, F. Agostini +116
We report on the response of liquid xenon to low energy electronic recoils below 15 keV from beta decays of tritium at drift fields of 92 V/cm, 154 V/cm and 366 V/cm using the XENO…
The XENON1T Dark Matter Experiment
XENON Collaboration, E. Aprile, J. Aalbers +142
The XENON1T experiment at the Laboratori Nazionali del Gran Sasso (LNGS) is the first WIMP dark matter detector operating with a liquid xenon target mass above the ton-scale. Out o…
Intrinsic backgrounds from Rn and Kr in the XENON100 experiment
XENON Collaboration, E. Aprile, J. Aalbers +115
In this paper, we describe the XENON100 data analyses used to assess the target-intrinsic background sources radon (Rn), thoron (Rn) and krypton (Kr). We det…
Effective field theory search for high-energy nuclear recoils using the XENON100 dark matter detector
E. Aprile, J. Aalbers, F. Agostini +114
We report on WIMP search results in the XENON100 detector using a non-relativistic effective field theory approach. The data from science run II (34 kg 224.6 live days) wa…