Results 111 to 120 of about 9,649,421 (248)

Enhancing point cloud semantic segmentation via scalable domain adaptation with LoRA-enabled PointNet++

ISPRS Open Journal of Photogrammetry and Remote Sensing
Semantic segmentation of airborne LiDAR point clouds enables a broad range of urban and environmental applications. However, domain shifts between training and operational data, as well as the frequent emergence of new semantic classes, pose significant ...
Mariona Carós, Ariadna Just, Santi Seguí, Jordi Vitrià   +3 more
doaj   +1 more source

GLoRIA : gated low-rank interpretable adaptation for dialectal ASR

Automatic Speech Recognition (ASR) in dialect-heavy settings remains challenging due to strong regional variation and limited labeled data. We propose GLoRIA, a parameter-efficient adaptation framework that leverages metadata (e.g., coordinates) to ...
Breitbarth, Anne, Ghyselen, Anne-Sophie, Farasyn, Melissa, Mehralian, Pouya, Van hamme, Hugo   +4 more
core   +1 more source

LORAMI: Low‐Rank Adaptation for Multi‐Identity Physics‐Based Face Rigs

Computer Graphics Forum, EarlyView.
Abstract Physics‐based simulation can augment facial rigs with high‐quality deformations, but at steep computational costs. While neural surrogates can substantially reduce computation time, existing methods do not generalize across identity variations and instead require expensive per‐case retraining.
D. Corigliano, D. Peter, B. Solenthaler, B. Thomaszewski   +3 more
wiley   +1 more source

Tier 2 adult weight management services in the UK: A case study evaluation of local authority provision of targeted services for higher‐risk groups in England

Clinical Obesity, Volume 15, Issue 2, April 2025.
Summary In 2021, the UK Government announced additional funding in England for Adult Weight Management Services (AWMS); it was specified that the extra funding must be used to commission or extend existing tier 2 services. The Office for Health Improvement and Disparities encouraged commissioners to prioritise services for higher‐risk groups such as ...
Lorraine McSweeney, Charlotte Rothwell, Ashley Adamson, Simon Barrett, Claire Mathews, Scott Lloyd, Mackenzie Fong   +6 more
wiley   +1 more source

Efficient encoder fine-tuning through configuration search and sparse low-rank adaptation

Machine Learning with Applications
Low-Rank Adaptation (LoRA) reduces the task-specific optimization burden of transformer fine-tuning, but its effectiveness remains sensitive to rank, placement, scaling, dropout, and training choices.
Seda Bayat Toksoz, Gultekin Isik, Hamidullah Turkmen, Ishak Pacal, Ayse Keles   +4 more
doaj   +1 more source

Parent–Student Communication in Colombian Universities: A Contribution to Academic Performance Analysis

Family Relations, EarlyView.
ABSTRACT Objective To examine the association between parent–student communication and academic performance (GPA) among Colombian university students. Background Family communication is an important dimension of students' academic experience, although its associations with academic performance may vary according to parental role, emotional tone, and ...
Lorena Cudris‐Torres, Álvaro Barrios‐Núñez, Jéssica Mejía Gutiérrez, Maira A. López‐Castellar, Jorge Armando Niño‐Vega, Flavio Humberto Fernández‐Morales, Pedro L. Medina‐Pulido, Natali Gaviria Arrieta, Stefano Vinaccia Alpi, Giselle Olivella‐López, Valmore Bermúdez   +10 more
wiley   +1 more source

Advancing Persistent Character Generation: Comparative Analysis of Fine-Tuning Techniques for Diffusion Models

AI
In the evolving field of artificial intelligence, fine-tuning diffusion models is crucial for generating contextually coherent digital characters across various media.
Luca Martini, Saverio Iacono, Daniele Zolezzi, Gianni Viardo Vercelli   +3 more
doaj   +1 more source

LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis

CoRR
Published at ICML ...
Qingyue Zhang, Chang Chu, Tianren Peng, Qi Li 0002, Xiangyang Luo 0001, Zhihao Jiang, Shao-Lun Huang   +6 more
openaire   +3 more sources

A Real‐Life, Multicenter, Retrospective Study on Epidemiological and Clinical Features of Patients With Hidradenitis Suppurativa and Concomitant Down Syndrome

International Journal of Dermatology, EarlyView.
Summary of the clinical characteristics and 2‐year follow‐up of patients with HS and concomitant DS in a multicentre Italian cohort, highlighting earlier HS onset, clinical features, and improved disease severity, quality of life, and pain over follow‐up, supporting early screening and multidisciplinary care of this special population.
Chiara Moltrasio, Luisa Sarno, Giovanni Genovese, Federica Derlino, Dalma Malvaso, Valeria Gaspari, Marina Venturini, Federica Repetto, Gianluca Avallone, Simone Ribero, Elisa Molinelli, Oriana Simonetti, Alessandra Michelucci, Marco Romanelli, Valentina Dini, Marco Manfredini, Cristina Magnoni, Caterina Foti, Silvia Sanna, Laura Atzori, Federico Bardazzi, Riccardo Balestri, Giulia Rech, Paolo Gisondi, Raffaele Dante Caposiena Caro, Iris Zalaudek, Viviana Lora, Luca Fania, Elia Rosi, Stefano Buffon, Carlo Alberto Maronese, Alessandra Cartocci, Pietro Rubegni, Francesca Prignano, Angelo Valerio Marzano   +34 more
wiley   +1 more source

TDA-L: Reducing Latency and Memory Consumption of Test-Time Adaptation for Real-Time Intelligent Sensing

Sensors
Vision–language models learn visual concepts from the supervision of natural language. It can significantly enhance the generalizability of real-time intelligent sensing, such as analyzing camera-captured real-time images for visually impaired users ...
Rahim Hossain, Md Tawheedul Islam Bhuian, Kyoung-Don Kang   +2 more
doaj   +1 more source