paper-with-me

Unsupervised Pre-training

2개 벤치마크 · 논문 277편 · 이 태스크의 논문 보기 →

Benchmarks

Measles

결과 5개

UCI measles

결과 3개

Most implemented

Papers

Unsupervised Multidomain Approaches to Named Entity Recognition with Small Datasets

2026-08-02 · Israel Fianyi, James Montgomery, Soonja Yeom arxiv

This paper explores the challenges and the methodologies associated with learning quality representations in scenarios with unlabelled small or limited datasets for downstream information extraction task (Multidomain Nam…

Unsupervised Pre-trainingInformation ExtractionData AugmentationTransfer Learning

From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training

2026-07-01 · Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang 외 arxiv

Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL). Given the large-scale action-free internet vide…

Unsupervised Pre-trainingReinforcement LearningImage ReconstructionContrastive Learning

PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking

2026-04-17 · Meng Lv, Yapeng Li, Hang Su, Juhua Liu 외 arxiv

Intelligent fetal ultrasound (US) interpretation is crucial for prenatal diagnosis, but high annotation costs and operator-induced variance make unsupervised pre-training a highly promising paradigm. However, existing pr…

Unsupervised Pre-training

Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution

2026-03-11 · Hongsong Wang, Renxi Cheng, Chaolei Han, Jie Gui arxiv

With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated by rapidly evolving imag…

Unsupervised Pre-trainingImage ClassificationDeepFake DetectionImage Attribution

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals

2026-01-27 · Octavio Pappalardo arxiv

Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks. A promising direction, grounded in human development, investigates agents that learn by …

Unsupervised Pre-trainingReinforcement Learning

Community Norms in the Spotlight: Enabling Task-Agnostic Unsupervised Pre-Training to Benefit Online Social Media

2026-01-26 · Liam Hebert, Lucas Kopp, Robin Cohen arxiv

Modelling the complex dynamics of online social platforms is critical for addressing challenges such as hate speech and misinformation. While Discussion Transformers, which model conversations as graph structures, have e…

Unsupervised Pre-training

전체 277편 보기 →