English
Related papers

Related papers: DuoTok: Source-Aware Dual-Track Tokenization for M…

200 papers

Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…

Computation and Language · Computer Science 2025-03-04 Kai Lv , Honglin Guo , Qipeng Guo , Xipeng Qiu

Three-dimensional ultrasound (US) offers many clinical advantages over conventional 2D imaging, yet its widespread adoption is limited by the cost and complexity of traditional 3D systems. Sensorless 3D US, which uses deep learning to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Paul F. R. Wilson , Matteo Ronchetti , Rüdiger Göbl , Viktoria Markova , Sebastian Rosenzweig , Raphael Prevost , Parvin Mousavi , Oliver Zettinig

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-30 Yang Yang , Yunpeng Li , George Sung , Shao-Fu Shih , Craig Dooley , Alessio Centazzo , Ramanan Rajeswaran

Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…

Computation and Language · Computer Science 2026-01-14 Adrian Cosma , Stefan Ruseti , Emilian Radoi , Mihai Dascalu

Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generative suitability. However, existing visual tokenizers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Shaobin Zhuang , Yuang Ai , Jiaming Han , Weijia Mao , Xiaohui Li , Fangyikang Wang , Xiao Wang , Yan Li , Shanchuan Lin , Kun Xu , Zhenheng Yang , Huaibo Huang , Xiangyu Yue , Hao Chen , Yali Wang

Machine systems inherently generate signals in which fault conditions and various variables influence signals measured from machine system. Although many existing fault classification studies rely solely on direct fault labels, the…

Machine Learning · Computer Science 2026-03-24 Wonjun Yi , Rismaya Kumar Mishra , Yong-Hwa Park

Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Jiawei Yang , Tianhong Li , Lijie Fan , Yonglong Tian , Yue Wang

Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative…

Sound · Computer Science 2025-02-12 Xiaoyu Bie , Xubo Liu , Gaël Richard

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Bowei Chen , Sai Bi , Hao Tan , He Zhang , Tianyuan Zhang , Zhengqi Li , Yuanjun Xiong , Jianming Zhang , Kai Zhang

Existing watermarking methods for audio generative models only enable model-level attribution, allowing the identification of the originating generation model, but are unable to trace the underlying training dataset. This significant…

Sound · Computer Science 2025-08-22 Xuefeng Yang , Jian Guan , Feiyang Xiao , Congyi Fan , Haohe Liu , Qiaoxi Zhu , Dongli Xu , Youtian Lin

We study two foundational problems in audio language models: (1) how to design an audio tokenizer that can serve as an intermediate representation for both understanding and generation; and (2) how to build an audio foundation model that…

Sound · Computer Science 2026-02-12 Dongchao Yang , Yuanyuan Wang , Dading Chong , Songxiang Liu , Xixin Wu , Helen Meng

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Computation and Language · Computer Science 2025-08-22 Dong Liu , Yanxuan Yu

Tokenization sits at the boundary between high-throughput genomic input and GPU compute, posing challenges in both algorithm design and system throughput. Overlapping k-mer tokenization can introduce information leakage under masked…

Genomics · Quantitative Biology 2026-01-12 Eliatan Niktab , Hardip Patel

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Hangyeol Lee , Hyojeong Lee , Joo-Young Kim

Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Chenyang Gu , Mingyuan Zhang , Haozhe Xie , Zhongang Cai , Lei Yang , Ziwei Liu

Extending pre-trained text Large Language Models (LLMs)'s speech understanding or generation abilities by introducing various effective speech tokens has attracted great attention in the speech community. However, building a unified speech…

Sound · Computer Science 2025-11-18 Yuanyuan Wang , Dongchao Yang , Yiwen Shao , Hangting Chen , Jiankun Zhao , Zhiyong Wu , Helen Meng , Xixin Wu

The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-17 Jingjing Chen , Qirong Mao , Dong Liu

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Anni Tang , Tianyu He , Junliang Guo , Xinle Cheng , Li Song , Jiang Bian

Neural audio codecs form the foundational building blocks for language model (LM)-based speech generation. Typically, there is a trade-off between frame rate and audio quality. This study introduces a low-frame-rate, semantically enhanced…

Sound · Computer Science 2025-10-02 Jiaqi Li , Xiaolong Lin , Zhekai Li , Shixi Huang , Yuancheng Wang , Chaoren Wang , Zhenpeng Zhan , Zhizheng Wu

Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Qihang Rao , Borui Zhang , Wenzhao Zheng , Jie Zhou , Jiwen Lu