English
Related papers

Related papers: SpacTor-T5: Pre-training T5 Models with Span Corru…

200 papers

Table structure recognition (TSR) aims to convert tabular images into a machine-readable format. Although hybrid convolutional neural network (CNN)-transformer architecture is widely used in existing approaches, linear projection…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 ShengYun Peng , Seongmin Lee , Xiaojing Wang , Rajarajeswari Balasubramaniyan , Duen Horng Chau

Multimodal language models can exhibit hallucinations in their outputs, which limits their reliability. The ability to automatically detect these errors is important for mitigating them, but has been less explored and existing efforts do…

Computation and Language · Computer Science 2024-09-04 Spencer Whitehead , Jacob Phillips , Sean Hendryx

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…

Software Engineering · Computer Science 2022-03-16 Deze Wang , Zhouyang Jia , Shanshan Li , Yue Yu , Yun Xiong , Wei Dong , Xiangke Liao

Deep learning (DL) techniques have been used to support several code-related tasks such as code summarization and bug-fixing. In particular, pre-trained transformer models are on the rise, also thanks to the excellent results they achieved…

The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed to reduce this gap, but most of them require architectural changes in ST training. In this work, we…

Computation and Language · Computer Science 2023-06-06 Phuong-Hang Le , Hongyu Gong , Changhan Wang , Juan Pino , Benjamin Lecouteux , Didier Schwab

Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods…

Machine Learning · Computer Science 2024-05-08 Peng-Fei Zhang , Zi Huang , Xin-Shun Xu , Guangdong Bai

Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an…

Computation and Language · Computer Science 2025-02-26 Fangyuan Yu

Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent progress, the scope of demonstration in SSL has mainly been on…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Kihyuk Sohn , Zizhao Zhang , Chun-Liang Li , Han Zhang , Chen-Yu Lee , Tomas Pfister

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

Computation and Language · Computer Science 2025-09-30 Yijun Tian , Shaoyu Chen , Zhichao Xu , Yawei Wang , Jinhe Bi , Peng Han , Wei Wang

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

Computation and Language · Computer Science 2023-06-12 Himanshu Gupta , Saurabh Arjun Sawant , Swaroop Mishra , Mutsumi Nakamura , Arindam Mitra , Santosh Mashetty , Chitta Baral

Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape capabilities during pretraining itself. On the proxy task of…

Machine Learning · Computer Science 2026-02-03 Neil Rathi , Alec Radford

Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), where contamination often goes beyond exact duplication. We present TRACER, a…

Software Engineering · Computer Science 2026-05-26 Yifeng Di , Xuliang Huang , Tianyi Zhang

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

Inspired by the great success of language model (LM)-based pre-training, recent studies in visual document understanding have explored LM-based pre-training methods for modeling text within document images. Among them, pre-training that…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Daehee Kim , Yoonsik Kim , DongHyun Kim , Yumin Lim , Geewook Kim , Taeho Kil

Vision transformers have been widely explored in various vision tasks. Due to heavy computational cost, much interest has aroused for compressing vision transformer dynamically in the aspect of tokens. Current methods mainly pay attention…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Fanhu Zeng , Deli Yu , Zhenglun Kong , Hao Tang

Real-time decoding of neural activity is central to neuroscience and neurotechnology applications, from closed-loop experiments to brain-computer interfaces, where models are subject to strict latency constraints. Traditional methods,…

Neurons and Cognition · Quantitative Biology 2025-11-10 Avery Hee-Woon Ryoo , Nanda H. Krishna , Ximeng Mao , Mehdi Azabou , Eva L. Dyer , Matthew G. Perich , Guillaume Lajoie

We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other. We test these models on the FigLang2022 shared task which…

Computation and Language · Computer Science 2022-11-01 Irina Bigoulaeva , Rachneet Sachdeva , Harish Tayyar Madabushi , Aline Villavicencio , Iryna Gurevych

The ubiquity of offensive content on social media is a growing cause for concern among companies and government organizations. Recently, transformer-based models such as BERT, XLNET, and XLM-R have achieved state-of-the-art performance in…

Computation and Language · Computer Science 2023-12-07 Tharindu Ranasinghe , Marcos Zampieri

This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language…

Computation and Language · Computer Science 2021-08-30 Mikhail Kotyushev , Anna Glazkova , Dmitry Morozov

Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and high computational cost, especially for small language models…

Machine Learning · Computer Science 2025-05-26 Xuechen Zhang , Zijian Huang , Chenshun Ni , Ziyang Xiong , Jiasi Chen , Samet Oymak