4 Contributo in Atti di Convegno (Proceeding)

4 Contributo in Atti di Convegno (Proceeding): [8355] Home page macrotipologia

Sfoglia

Prodotti recenti

Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison

Following the remarkable success of Large Language Models (LLMs) in NLP tasks, there is increasing interest in extending their capabilities to speech—the most common form of communication. The most widespread approach to integrating speech into LLMs is dense feature prepending (DFP), which prepends the projected speech representations to the textual representations, allowing end-to-end training with a speech encoder. This raises questions about the need for a sophisticated speech encoder for ...

Advanced X-ray PIxel Detector (AXPiDe v2.0): new modular multichannel detector based on SDD available at the XAFS beamline of Elettra

This contribution will report on a detection system specially designed and developed to fulfil the needs of X-ray Absorption Spectroscopy (XAS) experiments at the XAFS beamline of the ELETTRA synchrotron. It is composed of 8 monolithic multipixel arrays of Silicon Drift Detectors (SDDs), each comprising 8 cells (3x3 mm2) fabricated on 450-µm-thick, n-type, high-purity silicon wafers, and it includes a Tungsten collimation system. This results in 64 independent cells for a total collimated are...

High-Resolution Fabrication Procedure for an Optically-Transparent Modular Smart Electromagnetic Skin

A Smart ElectroMagnetic Environment (SEME) is enabled by introducing smart electromagnetic (EM) skins, or metasurfaces, with the final aim of manipulating the reflection and/or transmission properties to improve the wireless interconnectivity in non-line-of-sight areas. We focus on manufacturing of passive and static smart EM skins for wavefront manipulation, to enable optically transparent and conformable solutions. The most significant technological innovation of this contribution is the cr...

Towards the Reusability and Compositionality of Causal Representations

Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works focus on learning causal representations in a single environment, in this work we instead propose a first step towards learning causal representations from temporal sequences of images that can be adapted in a new environment, or composed across multiple related environments. In particular, we introduce DECAF,aframewo...

Latent Distillation for Continual Object Detection at the Edge

While numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) offers solutions to this issue, enabling models to adapt to new data while maintaining performance on previous data. This is particularly pertinent for edge devices, common in dynamic environments like automotive and robotics. In this work, we address the memory and computation constraints of edge devices in the Cont...

Scopri

Accesso al fulltext

no fulltext7398
open412
restricted379
reserved163
partially open2
mixed1

IRIS Institutional Research Information System