paper-with-me

Papers

Adaptor: Objective-Centric Adaptation Framework for Language Models

2022-03-08 · ACL 2022 5 · Michal Štefánik, Vít Novotný, Nikola Groverová, Petr Sojka

Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces Adaptor library that transposes the traditional model-centric approach composed of pre-training + fine-tuning steps to objective-centric approach, composing the training process by applications of selected objectives. We survey research directions that can benefit from enhanced objective-centric experimentation in multitask training, custom objectives development, dynamic training curricula, or domain adaptation. Adaptor aims to ease reproducibility of these research directions in practice. Finally, we demonstrate the practical applicability of Adaptor in selected unsupervised domain adaptation scenarios.

📄 PDF Abstract BibTeX arXiv:2203.03989

Code (1)

gaussalgo/adaptor 공식 구현 pytorch

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

All-in-One Transferring Image Compression from Human Perception to Multi-Machine Perception

2025-04-17 · Jiancheng Zhao, Xiang Ji, Zhuoxiao Li, Zunian Wan 외

Efficiently transferring Learned Image Compression (LIC) model from human perception to machine perception is an emerging challenge in vision-centric representation learning. Existing approaches typically adapt LIC to do…

AllImage CompressionRepresentation Learning

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

2026-05-31 · Zhuoyun Yu, Xin Xie, Wuguannan Yao, Chenxi Wang 외 arxiv

Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill adaptation pipelines usually update skills from full trajectories or s…

Self-Domain Adaptation for Face Anti-Spoofing

2021-02-24 · Jingjing Wang, Jingyi Zhang, Ying Bian, Youyi Cai 외

Although current face anti-spoofing methods achieve promising results under intra-dataset testing, they suffer from poor generalization to unseen attacks. Most existing works adopt domain adaptation (DA) or domain genera…

Domain AdaptationDomain GeneralizationFace Anti-SpoofingMeta-Learning

SODA: Robust Training of Test-Time Data Adaptors

2023-09-21 · NeurIPS 2023 11

Adapting models deployed to test distributions can mitigate the performance degradation caused by distribution shifts. However, privacy concerns may render model parameters inaccessible. One promising approach involves u…

Collaborative and Efficient Personalization with Mixtures of Adaptors

2024-10-04 · Abdulla Jasem Almansoori, Samuel Horváth, Martin Takáč

Non-iid data is prevalent in real-world federated learning problems. Data heterogeneity can come in different types in terms of distribution shifts. In this work, we are interested in the heterogeneity that comes from co…

Federated LearningMulti-Task Learning