English
Related papers

Related papers: TLM: Token-Level Masking for Transformers

200 papers

The transformer structure employed in large language models (LLMs), as a specialized category of deep neural networks (DNNs) featuring attention mechanisms, stands out for their ability to identify and highlight the most relevant aspects of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Matin Mortaheb , Erciyes Karakaya , Mohammad A. Amir Khojastepour , Sennur Ulukus

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, particularly with long…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Shilin Yan , Jiaming Han , Joey Tsai , Hongwei Xue , Rongyao Fang , Lingyi Hong , Ziyu Guo , Ray Zhang

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Machine Learning · Computer Science 2026-04-08 Jay Mohta , Kenan Emir Ak , Gwang Lee , Dimitrios Dimitriadis , Yan Xu , Mingwei Shen

Large-scale transformer models have become the de-facto architectures for various machine learning applications, e.g., CV and NLP. However, those large models also introduce prohibitive training costs. To mitigate this issue, we propose a…

Computation and Language · Computer Science 2022-11-22 Zhewei Yao , Xiaoxia Wu , Conglong Li , Connor Holmes , Minjia Zhang , Cheng Li , Yuxiong He

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token…

Computation and Language · Computer Science 2020-10-22 Huaao Zhang , Shigui Qiu , Xiangyu Duan , Min Zhang

Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explores an alternative axis: increasing per-token computation…

Computation and Language · Computer Science 2026-03-11 Boyi Zeng , Yiqin Hao , He Li , Shixiang Song , Feichen Song , Zitong Wang , Siyuan Huang , Yi Xu , ZiWei He , Xinbing Wang , Zhouhan Lin

Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models. As the most successful LMs are based on the Transformer architecture, processing these long token streams with…

Computation and Language · Computer Science 2026-02-05 Nicholas Lee , Cheol Jun Cho , Alan W Black , Gopala K. Anumanchipalli

This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…

Computation and Language · Computer Science 2025-01-24 Jia Gao , Guiran Liu , Binrong Zhu , Shicheng Zhou , Hongye Zheng , Xiaoxuan Liao

Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…

Machine Learning · Computer Science 2022-07-18 Bowen Zhao , Huanlai Xing , Xinhan Wang , Fuhong Song , Zhiwen Xiao

Deploying transformer models in practice is challenging due to their inference cost, which scales quadratically with input sequence length. To address this, we present a novel Learned Token Pruning (LTP) method which adaptively removes…

Computation and Language · Computer Science 2022-06-06 Sehoon Kim , Sheng Shen , David Thorsley , Amir Gholami , Woosuk Kwon , Joseph Hassoun , Kurt Keutzer

In autonomous driving, end-to-end (E2E) driving systems that predict control commands directly from sensor data have achieved significant advancements. For safe driving in unexpected scenarios, these systems may additionally rely on human…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Seo Hyun Kim , Jin Bok Park , Do Yeon Koo , Hogun Park , Il Yong Chun

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies…

Computation and Language · Computer Science 2025-08-15 Shuhai Zhang , Zeng You , Yaofo Chen , Zhiquan Wen , Qianyue Wang , Zhijie Qiu , Yuanqing Li , Mingkui Tan

Large Language Models (LLMs) for complex reasoning is often hindered by high computational costs and latency, while resource-efficient Small Language Models (SLMs) typically lack the necessary reasoning capacity. Existing collaborative…

Computation and Language · Computer Science 2026-01-09 Chengsong Huang , Tong Zheng , Langlin Huang , Jinyuan Li , Haolin Liu , Jiaxin Huang

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…

Computation and Language · Computer Science 2019-09-05 Elena Voita , Rico Sennrich , Ivan Titov

In activity recognition, it is often expensive and time-consuming to acquire sufficient activity labels. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has…

Computer Vision and Pattern Recognition · Computer Science 2018-01-04 Jindong Wang , Yiqiang Chen , Lisha Hu , Xiaohui Peng , Philip S. Yu

Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to…

Computation and Language · Computer Science 2020-03-25 Kevin Clark , Minh-Thang Luong , Quoc V. Le , Christopher D. Manning

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

Advances in mechanistic interpretability have identified special attention heads, known as retrieval heads, that are responsible for retrieving information from the context. However, the role of these retrieval heads in improving model…

Computation and Language · Computer Science 2026-04-27 Youmi Ma , Naoaki Okazaki

Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. However, modeling human language at higher-levels of context…

Computation and Language · Computer Science 2021-11-03 Matthew Matero , Nikita Soni , Niranjan Balasubramanian , H. Andrew Schwartz