English
Related papers

Related papers: Self-Supervised Test-Time Learning for Reading Com…

200 papers

Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions. To address this…

Sound · Computer Science 2022-10-27 Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao

Long-context modeling presents a significant challenge for transformer-based large language models (LLMs) due to the quadratic complexity of the self-attention mechanism and issues with length extrapolation caused by pretraining exclusively…

Computation and Language · Computer Science 2024-05-24 Chenghao Yang , Zi Yang , Nan Hua

The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the label-embedded DL methods rely on the labels due that this way…

Machine Learning · Computer Science 2021-12-06 Shuai Shao , Lei Xing , Wei Yu , Rui Xu , Yanjiang Wang , Baodi Liu

We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Previous efforts to construct such datasets relied on crowd-sourcing, but the emergence of…

Large language models (LLMs) exploit in-context learning (ICL) to solve tasks with only a few demonstrations, but its mechanisms are not yet well-understood. Some works suggest that LLMs only recall already learned concepts from…

Computation and Language · Computer Science 2023-05-18 Jane Pan , Tianyu Gao , Howard Chen , Danqi Chen

An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however,…

Computer Vision and Pattern Recognition · Computer Science 2022-01-21 Alexander Bartler , Andre Bühler , Felix Wiewel , Mario Döbler , Bin Yang

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled…

Computer Vision and Pattern Recognition · Computer Science 2020-06-09 Florent Chiaroni , Mohamed-Cherif Rahal , Nicolas Hueber , Frederic Dufaux

The effectiveness of unlabeled data in Semi/Self-Supervised Learning (SSL) depends on appropriate assumptions for specific scenarios, thereby enabling the selection of beneficial unsupervised pretext tasks. However, existing research has…

Machine Learning · Computer Science 2026-04-09 Lin-Han Jia , Si-Yu Han , Wen-Chao Hu , Jie-Jing Shao , Wen-Da Wei , Zhi Zhou , Lan-Zhe Guo , Yu-Feng Li

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…

Machine Learning · Computer Science 2020-07-03 Huanru Henry Mao

Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream…

Computation and Language · Computer Science 2022-06-17 Hyuhng Joon Kim , Hyunsoo Cho , Junyeob Kim , Taeuk Kim , Kang Min Yoo , Sang-goo Lee

Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's prediction (i.e. the pseudo-parallel data). While self-training…

Machine Learning · Computer Science 2020-10-20 Junxian He , Jiatao Gu , Jiajun Shen , Marc'Aurelio Ranzato

Recently, very large language models (LLMs) have shown exceptional performance on several English NLP tasks with just in-context learning (ICL), but their utility in other languages is still underexplored. We investigate their effectiveness…

Computation and Language · Computer Science 2024-06-28 Vipul Rathore , Aniruddha Deb , Ankish Chandresh , Parag Singla , Mausam

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its semantics, syntax,…

Computation and Language · Computer Science 2024-02-22 Lei Pan , Yunshi Lan , Yang Li , Weining Qian

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…

Computation and Language · Computer Science 2020-10-06 Jingfei Du , Edouard Grave , Beliz Gunel , Vishrav Chaudhary , Onur Celebi , Michael Auli , Ves Stoyanov , Alexis Conneau

Handwritten Text Recognition (HTR) is a relevant problem in computer vision, and implies unique challenges owing to its inherent variability and the rich contextualization required for its interpretation. Despite the success of…

Artificial Intelligence · Computer Science 2025-06-19 Carlos Penarrubia , Carlos Garrido-Munoz , Jose J. Valero-Mas , Jorge Calvo-Zaragoza

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Liangzhe Yuan , Rui Qian , Yin Cui , Boqing Gong , Florian Schroff , Ming-Hsuan Yang , Hartwig Adam , Ting Liu

Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding text and generating high-quality responses. However, a critical distinction from human cognition is their typical lack of a distinct internal `reading'…

Computation and Language · Computer Science 2025-07-08 Yuanxin Wang , Ganesh Venkatesh

Existing test-time scaling (TTS) methods for unified multimodal models (UMMs) in text-to-image (T2I) generation primarily rely on search or sampling strategies that produce only instance-level improvements, limiting the ability to learn…

Machine Learning · Computer Science 2026-03-18 Lit Sin Tan , Junzhe Chen , Xiaolong Fu , Lichen Ma , Junshi Huang , Jianzhong Shi , Yan Li , Lijie Wen

Unsupervised learning has been an attractive method for easily deriving meaningful data representations from vast amounts of unlabeled data. These representations, or embeddings, often yield superior results in many tasks, whether used…

Computation and Language · Computer Science 2018-11-02 Shao-Yen Tseng , Brian Baucom , Panayiotis Georgiou

In order to train robust deep learning models, large amounts of labelled data is required. However, in the absence of such large repositories of labelled data, unlabeled data can be exploited for the same. Semi-Supervised learning aims to…

Machine Learning · Computer Science 2021-07-20 Soumyadeep Ghosh , Sanjay Kumar , Janu Verma , Awanish Kumar