Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily on manual trial-and-error processes, incur significant hyperparameter complexity, and are highly sensitive to data and user preferences, all under the high cost of LLM training. Moreover, the interactions and transferability of hyperparameter choices across models/domains remain poorly understood, making adaptation gains uncertain even with substantial effort. To solve these challenges, we present AutoAdapt, a novel end-to-end automated framework for efficient and reliable LLM domain adaptation. AutoAdapt leverages curated knowledge bases from literature and open-source resources to reduce expert intervention. To narrow the search space, we design a novel multi-agent debating system in which proposal and critic agents iteratively interact to align user intent and incorporate data signals and best practices into the planning process. To optimize hyperparameters under tight budgets, we propose AutoRefine, a novel LLM-based surrogate that replaces costly black-box search. Across 10 tasks, AutoAdapt achieves a 25% average relative accuracy improvement over state-of-the-art Automated Machine Learning baselines with minimal overhead.
Domain Adaptation of Automated Treatment Planning from Computed Tomography to Magnetic Resonance
University of Toronto(多伦多大学);Techna Institute, University Health Network(大学健康网络泰克纳研究所);Princess Margaret Cancer Center(玛格丽特公主癌症中心);Peter Munk Cardiac Center, University Health Network(大学健康网络彼得·蒙克心脏中心);Joint Department of Medical Imaging, University Health Network(大学健康网络医学影像联合部);Vector Institute(矢量研究所)
LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification
School of Mechano-Electronic Engineering Xidian University Xi'an, China(机械电子工程学院 西安电子科技大学 西安中国);School of Cyber Engineering Xidian University Xi'an, China(网络工程学院 西安电子科技大学 西安中国);DCST, BNRist, RIIT, Institute of Internet Industry Tsinghua University Beijing, China(DCST、BNRist、RIIT、互联网产业研究院 清华大学 北京中国)
Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition
University of California, Berkeley(加州大学伯克利分校);Amazon Alexa AI(亚马逊Alexa人工智能部门)
尽管自动语音识别(ASR)模型的泛化性能有所改进,但针对下游任务的专用ASR模型仍然是一项具有挑战性的任务,这主要是由于数据可用性降低(需要增加数据收集)和数据分布快速变化(需要更频繁的模型微调)。在这项工作中,我们研究了利用外部知识的潜力,特别是通过使用文本到语音方法生成的非策略键值存储,以允许灵活的训练后适应新的数据分布。在我们的方法中,从文本到语音捕获的音频嵌入,以及语义文本嵌入,用于通过基于近似k-最近邻(KNN)的专注融合步骤来偏置ASR。我们在LibiriSpeech和内部语音助手/搜索数据集上的实验表明,与微调基线相比,所提出的方法可以将域适应时间减少多达1 K GPU小时,同时提供高达3%的WER改进,这表明在具有挑战性的零和Few-Shot场景中适应生产ASR系统的方法很有前途。
A Domain Adaptation of Large Language Models for Classifying Mechanical Assembly Components
School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ(Arizona State大学计算机与增强智能学院);Autodesk, San Francisco, CA(Autodesk公司);School of Manufacturing Systems and Networks, Arizona State University, Mesa, AZ(Arizona State大学制造系统与网络学院)
Test-Time Adaptation in Optical Coherence Tomography Using Trajectory-Aligned Time-Independent Flow
Institute of Artificial Intelligence, Center for Medical Data Science, Medical University of Vienna, Austria(人工智能研究所、医学数据科学中心、维也纳医学大学,奥地利);Comprehensive Center for Artificial Intelligence in Medicine, Medical University of Vienna, Austria(医学人工智能综合中心、维也纳医学大学,奥地利);Department of Ophthalmology and Optometry, Medical University of Vienna, Austria(眼科与视光学部、维也纳医学大学,奥地利);Laboratory for Ophthalmic Image Analysis, Medical University of Vienna, Austria(眼科图像分析实验室、维也纳医学大学,奥地利)
Unsupervised Adversarial Domain Adaptation For Barrett's Segmentation
University of Oxford(牛津大学);NIHR Oxford Biomedical Research Centre(NIHR牛津生物医学研究中心);Oxford University Hospitals NHS Foundation Trust(牛津大学医院NHS基金会信托);John Radcliffe Hospital(约翰·拉德克利夫医院)
STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification
School of Computing, Wichita State University(维斯科州立大学计算机学院);Computer Science and Engineering Department, University of Nevada, Reno(内华达大学里诺分校计算机科学与工程系)
Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence
Singapore University of Design and Technology(新加坡科技设计大学);East China Normal University(华东师范大学);University of Electronic Science and Technology of China(电子科技大学);Beihang University(北京航空航天大学)
CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety
Department of Computer Science, Virginia Tech(弗吉尼亚理工大学计算机科学系);School of IT(信息技术学院);Engineering, ADA University(工程学院,ADA大学);School of Law, ADA University(法学院,ADA大学)