paper-with-me

Papers

Low-resource domain adaptation while minimizing energy and hardware resource consumption

2025-06-10 · Hernán Maina, Nicolás Wolovick, Luciana Benotti

Training Large Language Models (LLMs) is costly in terms of energy, hardware, and annotated data, often resulting in a positionality rooted in predominant cultures and values (Santy et al., 2023). Domain adaptation has emerged as a promising strategy to better align models with diverse cultural and value contexts (Hershcovich et al., 2022), but its computational cost remains a significant barrier, particularly for research groups lacking access to large-scale infrastructure. In this paper, we evaluate how the use of different numerical precision formats and data parallelization strategies impacts both training speed (as a proxy to energy and hardware consumption) and model accuracy, with the goal of facilitating domain adaptation in low-resource environments. Our findings are relevant to any setting where energy efficiency, accessibility, or limited hardware availability are key concerns.

📄 PDF Abstract BibTeX arXiv:2506.08433

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

ALERT: Accurate Learning for Energy and Timeliness

2019-10-31 · Chengcheng Wan, Muhammad Santriaji, Eri Rogers, Henry Hoffmann 외

An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of DNNs in these interactive scenarios req…

CPUGPUImage Classification

Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation

2025-07-14 · Manuel Röder, Christoph Raab, Frank-Michael Schleif

Federated Learning has emerged as a leading paradigm for decentralized, privacy-preserving learning, particularly relevant in the era of interconnected edge devices equipped with sensors. However, the practical implement…

Domain AdaptationFederated LearningPrivacy Preserving

On-demand Test-time Adaptation for Edge Devices

2025-05-02 · Xiao Ma, Young D. Kwon, Dong Ma

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-c…

Test-time Adaptation

ORIENT: A Priority-Aware Energy-Efficient Approach for Latency-Sensitive Applications in 6G

2024-02-10 · Masoud Shokrnezhad, Tarik Taleb

Anticipation for 6G's arrival comes with growing concerns about increased energy consumption in computing and networking. The expected surge in connected devices and resource-demanding applications presents unprecedented…

Q-Learning

Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning

2026-05-24 · Yu Yang, Yihong Guo, Anqi Liu, Pan Xu arxiv

Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Existing approaches such as reward augmenta…

Reinforcement LearningOffline RL