English
Related papers

Related papers: ENTP: Encoder-only Next Token Prediction

200 papers

Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods typically demand massive computation resources. To accelerate…

Computation and Language · Computer Science 2022-03-04 Jiaming Shen , Jialu Liu , Tianqi Liu , Cong Yu , Jiawei Han

This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facilitate faster recognition. We provide a comprehensive comparison of techniques to integrate…

Computation and Language · Computer Science 2026-04-30 Albert Zeyer , Tim Posielek , Ralf Schlüter , Hermann Ney

Starting from NMT, encoder-decoder neu- ral networks have been used for many NLP problems. Graph-based models and transition-based models borrowing the en- coder components achieve state-of-the-art performance on dependency parsing and…

Computation and Language · Computer Science 2017-06-27 Jiangming Liu , Yue Zhang

Predicting the next utterance in dialogue is contingent on encoding of users' input text to generate appropriate and relevant response in data-driven approaches. Although the semantic and syntactic quality of the language generated is…

Computation and Language · Computer Science 2021-06-22 Prasanna Parthasarathi , Joelle Pineau , Sarath Chandar

Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with…

In this short report, we introduce joint multi-token prediction (JTP), a lightweight modification of standard next-token prediction designed to enrich hidden state representations by jointly predicting multiple future tokens. Unlike…

Machine Learning · Computer Science 2025-03-31 Kwangjun Ahn , Alex Lamb , John Langford

This paper proposes Progressive Inference - a framework to compute input attributions to explain the predictions of decoder-only sequence classification models. Our work is based on the insight that the classification head of a decoder-only…

Machine Learning · Computer Science 2024-06-06 Sanjay Kariyappa , Freddy Lécué , Saumitra Mishra , Christopher Pond , Daniele Magazzeni , Manuela Veloso

Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks trained on the simple task of next-token prediction. In…

Machine Learning · Computer Science 2024-07-31 Eran Malach

Next token prediction is an attractive pre-training task for jet foundation models, in that it is simulation free and enables excellent generative capabilities that can transfer across datasets. Here we study multiple improvements to next…

High Energy Physics - Phenomenology · Physics 2025-12-05 Joschka Birk , Anna Hallin , Gregor Kasieczka , Nikol Madzharova , Ian Pang , David Shih

Standard next-token prediction (NTP) supervises language models solely through discrete labels in the output logit space. We argue that this sparse one-hot supervision leaves the latent representation space under-constrained, allowing…

Computation and Language · Computer Science 2026-05-26 Xiangdong Zhang , Debing Zhang , Shaofeng Zhang , Xiaohan Qin , Yu Cheng , Junchi Yan

Pre-trained encoder-decoder transformer architectures have become increasingly popular recently with the advent of T5 models. T5 has also become more favorable over other architectures like BERT due to the amount of data that it is…

Computation and Language · Computer Science 2022-10-25 Frederick Liu , Terry Huang , Shihang Lyu , Siamak Shakeri , Hongkun Yu , Jing Li

Neural methods of molecule property prediction require efficient encoding of structure and property relationship to be accurate. Recent work using graph algorithms shows limited generalization in the latent molecule encoding space. We build…

Quantitative Methods · Quantitative Biology 2020-11-26 Prateeth Nayak , Andrew Silberfarb , Ran Chen , Tulay Muezzinoglu , John Byrnes

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Yangyang Xu , Yibo Yang , Lefei Zhang

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Computation and Language · Computer Science 2025-03-03 Rachel Wicks , Kartik Ravisankar , Xinchen Yang , Philipp Koehn , Matt Post

End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Maoyuan Ye , Jing Zhang , Shanshan Zhao , Juhua Liu , Tongliang Liu , Bo Du , Dacheng Tao

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…

Computation and Language · Computer Science 2021-12-15 Pierre Beckmann , Mikolaj Kegler , Milos Cernak

Next token prediction paradigm has been prevailing for autoregressive models in the era of LLMs. The current default sampling choice for popular LLMs is temperature scaling together with nucleus sampling to balance diversity and coherence.…

Computation and Language · Computer Science 2025-07-24 Yizhou Wang , Lingzhi Zhang , Yue Bai , Mang Tik Chiu , Zhengmian Hu , Mingyuan Zhang , Qihua Dong , Yu Yin , Sohrab Amirghodsi , Yun Fu

Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks…

Computation and Language · Computer Science 2022-10-18 Ewa Andrejczuk , Julian Martin Eisenschlos , Francesco Piccinno , Syrine Krichene , Yasemin Altun

Predicting the motion of other agents in a scene is highly relevant for autonomous driving, as it allows a self-driving car to anticipate. Inspired by the success of decoder-only models for language modeling, we propose DONUT, a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Markus Knoche , Daan de Geus , Bastian Leibe

DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing. However, it suffers from problems such as low performance and slow convergence. A series of works aim to tackle these issues in…

Computer Vision and Pattern Recognition · Computer Science 2022-03-03 Junyu Lin , Xiaofeng Mao , Yuefeng Chen , Lei Xu , Yuan He , Hui Xue