English
Related papers

Related papers: Multi-Token Prediction Needs Registers

200 papers

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training…

Computation and Language · Computer Science 2023-05-25 Qihuang Zhong , Liang Ding , Juhua Liu , Xuebo Liu , Min Zhang , Bo Du , Dacheng Tao

Turn-taking, aiming to decide when the next speaker can start talking, is an essential component in building human-robot spoken dialogue systems. Previous studies indicate that multimodal cues can facilitate this challenging task. However,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-22 Jiudong Yang , Peiying Wang , Yi Zhu , Mingchao Feng , Meng Chen , Xiaodong He

Generative recommendation autoregressively generates item identifiers to recommend potential items. Existing methods typically adopt a one-to-one mapping strategy, where each item is represented by a single identifier. However, this scheme…

Information Retrieval · Computer Science 2025-05-27 Bowen Zheng , Enze Liu , Zhongfu Chen , Zhongrui Ma , Yue Wang , Wayne Xin Zhao , Ji-Rong Wen

Motion prediction is crucial for autonomous driving systems to understand complex driving scenarios and make informed decisions. However, this task is challenging due to the diverse behaviors of traffic participants and complex…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Shaoshuai Shi , Li Jiang , Dengxin Dai , Bernt Schiele

The application of data-driven remaining useful life (RUL) prediction has long been constrained by the availability of large amount of degradation data. Mainstream solutions such as domain adaptation and meta-learning still rely on large…

Machine Learning · Computer Science 2026-02-02 En Fu , Yanyan Hu , Changhua Hu , Zengwang Jin , Kaixiang Peng

MLtuner automatically tunes settings for training tunables (such as the learning rate, the momentum, the mini-batch size, and the data staleness bound) that have a significant impact on large-scale machine learning (ML) performance.…

Machine Learning · Computer Science 2018-03-21 Henggang Cui , Gregory R. Ganger , Phillip B. Gibbons

Fine-tuned pre-trained language models (PLMs) have achieved awesome performance on almost all NLP tasks. By using additional prompts to fine-tune PLMs, we can further stimulate the rich knowledge distributed in PLMs to better serve…

Computation and Language · Computer Science 2021-09-16 Xu Han , Weilin Zhao , Ning Ding , Zhiyuan Liu , Maosong Sun

Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement…

Computation and Language · Computer Science 2025-09-04 Yarden Tzach , Ronit D. Gross , Ella Koresh , Shalom Rosner , Or Shpringer , Tal Halevi , Ido Kanter

Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Yen-Chun Chen , Linjie Li , Licheng Yu , Ahmed El Kholy , Faisal Ahmed , Zhe Gan , Yu Cheng , Jingjing Liu

Prompt tuning, like CoOp, has recently shown promising vision recognizing and transfer learning ability on various downstream tasks with the emergence of large pre-trained vision-language models like CLIP. However, we identify that existing…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Yongzhu Miao , Shasha Li , Jintao Tang , Ting Wang

Recent advances in multimodal agents have improved computer-use interaction and tool-usage, yet most existing systems remain reactive, optimizing actions in isolation without reasoning about future states or long-term goals. This limits…

Artificial Intelligence · Computer Science 2026-03-18 Yongyuan Liang , Shijie Zhou , Yu Gu , Hao Tan , Gang Wu , Franck Dernoncourt , Jihyung Kil , Ryan A. Rossi , Ruiyi Zhang

It is expensive to evaluate the results of Machine Translation(MT), which usually requires manual translation as a reference. Machine Translation Quality Estimation (QE) is a task of predicting the quality of machine translations without…

Computation and Language · Computer Science 2022-04-19 Lei Lin

The objective of this paper is an efficient training method for video tasks. We make three contributions: (1) We propose Turbo training, a simple and versatile training paradigm for Transformers on multiple video tasks. (2) We illustrate…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Tengda Han , Weidi Xie , Andrew Zisserman

The goal of sequential recommendation (SR) is to predict a user's potential interested items based on her/his historical interaction sequences. Most existing sequential recommenders are developed based on ID features, which, despite their…

Information Retrieval · Computer Science 2023-10-24 Jinpeng Wang , Ziyun Zeng , Yunxiao Wang , Yuting Wang , Xingyu Lu , Tianxiang Li , Jun Yuan , Rui Zhang , Hai-Tao Zheng , Shu-Tao Xia

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…

Computation and Language · Computer Science 2023-03-07 Zhen Wang , Rameswar Panda , Leonid Karlinsky , Rogerio Feris , Huan Sun , Yoon Kim

We present a simple and effective pretraining strategy {D}en{o}ising {T}raining DoT for neural machine translation. Specifically, we update the model parameters with source- and target-side denoising tasks at the early stage and then tune…

Computation and Language · Computer Science 2022-01-21 Liang Ding , Keqin Peng , Dacheng Tao

Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and…

Computation and Language · Computer Science 2025-07-04 Tao Xiong , Xavier Hu , Wenyan Fan , Shengyu Zhang

Simultaneous machine translation is a variant of machine translation that starts the translation process before the end of an input. This task faces a trade-off between translation accuracy and latency. We have to determine when we start…

Computation and Language · Computer Science 2019-11-28 Katsuki Chousa , Katsuhito Sudoh , Satoshi Nakamura

Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of…

We propose a modular architecture of language-specific encoder-decoders that constitutes a multilingual machine translation system that can be incrementally extended to new languages without the need for retraining the existing system when…

Computation and Language · Computer Science 2020-06-03 Carlos Escolano , Marta R. Costa-jussà , José A. R. Fonollosa , Mikel Artetxe