English
Related papers

Related papers: Adaptive Protein Tokenization

200 papers

Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…

Computation and Language · Computer Science 2025-08-11 Alistair Dombrowski , Beatrix Engelhardt , Dimitri Fairbrother , Henry Evidail

Proteins are responsible for the most diverse set of functions in biology. The ability to extract information from protein sequences and to predict the effects of mutations is extremely valuable in many domains of biology and medicine.…

Quantitative Methods · Quantitative Biology 2018-01-04 Sam Sinai , Eric Kelsic , George M. Church , Martin A. Nowak

The protein design problem involves finding polypeptide sequences folding into a given threedimensional structure. Its rigorous algorithmic solution is computationally demanding, involving a nested search in sequence and structure spaces.…

Quantum Physics · Physics 2024-07-11 Veronica Panizza , Philipp Hauke , Cristian Micheletti , Pietro Faccioli

This paper proposes a fundamentally new paradigm for image generation through set-based tokenization and distribution modeling. Unlike conventional methods that serialize images into fixed-position latent codes with a uniform compression…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Zigang Geng , Mengde Xu , Han Hu , Shuyang Gu

Simulating interactions between deformable bodies is vital in fields like material science, mechanical design, and robotics. While learning-based methods with Graph Neural Networks (GNNs) are effective at solving complex physical systems,…

Machine Learning · Computer Science 2025-07-21 Hao Wang , Yu Liu , Daniel Biggs , Haoru Wang , Jiandong Yu , Ping Huang

Is there a foreign language describing protein sequences and structures simultaneously? Protein structures, represented by continuous 3D points, have long posed a challenge due to the contrasting modeling paradigms of discrete sequences. We…

Biomolecules · Quantitative Biology 2024-03-20 Zhangyang Gao , Cheng Tan , Jue Wang , Yufei Huang , Lirong Wu , Stan Z. Li

Molecular representation learning methods typically tokenize molecules as individual atoms or use rigid, rule-based fragment decompositions, limiting their ability to capture meaningful chemical substructure context. We introduce…

Machine Learning · Computer Science 2026-05-26 Ankur Samanta , Rohan Gupta , Aditi Misra , Christian McIntosh Clarke , Jayakumar Rajadas

Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to…

Computation and Language · Computer Science 2026-05-14 Abraham Toluwase Owodunni , Orevaoghene Ahia , Sachin Kumar

Machine-learning models that learn from data to predict how protein sequence encodes function are emerging as a useful protein engineering tool. However, when using these models to suggest new protein designs, one must deal with the vast…

Quantitative Methods · Quantitative Biology 2021-07-07 Brian L. Hie , Kevin K. Yang

Human visual recognition system shows astonishing capability of compressing visual information into a set of tokens containing rich representations without label supervision. One critical driving principle behind it is perceptual grouping.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-26 Zhiwei Deng , Ting Chen , Yang Li

Subword tokenization methods, such as Byte-Pair Encoding (BPE), significantly impact the performance and efficiency of large language models (LLMs). The standard approach involves training a general-purpose tokenizer that uniformly…

Computation and Language · Computer Science 2026-01-30 Vijini Liyanage , François Yvon

Foundation models have made significant strides in understanding the genomic language of DNA sequences. However, previous models typically adopt the tokenization methods designed for natural language, which are unsuitable for DNA sequences…

Genomics · Quantitative Biology 2024-12-19 Lifeng Qiao , Peng Ye , Yuchen Ren , Weiqiang Bai , Chaoqi Liang , Xinzhu Ma , Nanqing Dong , Wanli Ouyang

Despite the high-quality results of text-to-image generation, stereotypical biases have been spotted in their generated contents, compromising the fairness of generative models. In this work, we propose to learn adaptive inclusive tokens to…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Xinyu Hou , Xiaoming Li , Chen Change Loy

Many algorithms and applications involve repeatedly solving variations of the same inference problem; for example we may want to introduce new evidence to the model or perform updates to conditional dependencies. The goal of adaptive…

Data Structures and Algorithms · Computer Science 2012-06-18 Umut A. Acar , Alexander T. Ihler , Ramgopal Mettu , Ozgur Sumer

Deep learning approaches have produced substantial breakthroughs in fields such as image classification and natural language processing and are making rapid inroads in the area of protein design. Many generative models of proteins have been…

Machine Learning · Computer Science 2021-09-29 Alexey Strokach , Philip M. Kim

Foundation models in language and vision benefit from a unified discrete token interface that converts raw inputs into sequences for scalable pre-training and inference. For graphs, an effective tokenizer should yield reusable discrete…

Information Retrieval · Computer Science 2026-05-28 Yang Xiang , Li Fan , Chenke Yin , Lutz Oettershagen , Chengtao Ji

This study introduces a novel knowledge enhanced tokenisation mechanism, K-Tokeniser, for clinical text processing. Technically, at initialisation stage, K-Tokeniser populates global representations of tokens based on semantic types of…

Computation and Language · Computer Science 2024-06-21 Abul Hasan , Jinge Wu , Quang Ngoc Nguyen , Salomé Andres , Imane Guellil , Huayu Zhang , Arlene Casey , Beatrice Alex , Bruce Guthrie , Honghan Wu

Protein structure tokenizers (PSTs) are workhorses in protein language modeling, function prediction, and evolutionary analysis. However, existing PSTs only capture local geometry of static structures, and miss the correlated motions and…

Machine Learning · Computer Science 2026-05-15 Kaiwen Shi , Carlos Oliver

Tokenization - the practice of converting strings of characters from an alphabet into sequences of tokens over a vocabulary - is a critical step in the NLP pipeline. The use of token representations is widely credited with increased model…

Computation and Language · Computer Science 2025-04-04 Juan Luis Gastaldi , John Terilla , Luca Malagutti , Brian DuSell , Tim Vieira , Ryan Cotterell

Many 3D generative models rely on variational autoencoders (VAEs) to learn compact shape representations. However, existing methods encode all shapes into a fixed-size token, disregarding the inherent variations in scale and complexity…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Kangle Deng , Hsueh-Ti Derek Liu , Yiheng Zhu , Xiaoxia Sun , Chong Shang , Kiran Bhat , Deva Ramanan , Jun-Yan Zhu , Maneesh Agrawala , Tinghui Zhou