English
Related papers

Related papers: Compute Optimal Tokenization

200 papers

How can we compress language models without sacrificing accuracy? The number of compression algorithms for language models is rapidly growing to benefit from remarkable advances of recent language models without side effects due to the…

Computation and Language · Computer Science 2024-01-30 Seungcheol Park , Jaehyeon Choi , Sojin Lee , U Kang

Research on scaling large language models (LLMs) has primarily focused on model parameters and training data size, overlooking the role of vocabulary size. We investigate how vocabulary size impacts LLM scaling laws by training models…

Computation and Language · Computer Science 2024-11-04 Chaofan Tao , Qian Liu , Longxu Dou , Niklas Muennighoff , Zhongwei Wan , Ping Luo , Min Lin , Ngai Wong

Compressing large language models (LLMs), often consisting of billions of parameters, provides faster inference, smaller memory footprints, and enables local deployment. Two standard compression techniques are pruning and quantization, with…

Computation and Language · Computer Science 2023-12-05 Satya Sai Srinath Namburi , Makesh Sreedhar , Srinath Srinivasan , Frederic Sala

The computational and energy costs of Large Language Models (LLMs) have increased exponentially driven by the growing model sizes and the massive adoption of LLMs by hundreds of millions of users. The unit cost of an LLM is the computation…

Computation and Language · Computer Science 2025-06-24 Raquel Ferrando , Javier Conde , Gonzalo Martínez , Pedro Reviriego

Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets. This provides an efficient way for practitioners and researchers alike to compare…

Machine Learning · Computer Science 2025-06-04 Leshem Choshen , Yang Zhang , Jacob Andreas

The recent success of Large Language Models (LLMs) has been predominantly driven by curating the training dataset composition, scaling of model architectures and dataset sizes and advancements in pretraining objectives, leaving tokenizer…

Why do larger language models generalize better? To investigate this question, we develop generalization bounds on the pretraining objective of large language models (LLMs) in the compute-optimal regime, as described by the Chinchilla…

Machine Learning · Computer Science 2025-04-22 Marc Finzi , Sanyam Kapoor , Diego Granziol , Anming Gu , Christopher De Sa , J. Zico Kolter , Andrew Gordon Wilson

While 4-bit quantization has emerged as a memory-optimal choice for non-reasoning models and zero-shot tasks across scales, we show that this universal prescription fails for reasoning models, where the KV cache rather than model size can…

Machine Learning · Computer Science 2025-10-14 Junhyuck Kim , Ethan Ewer , Taehong Moon , Jongho Park , Dimitris Papailiopoulos

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

Computation and Language · Computer Science 2025-06-03 Shunsuke Kando , Yusuke Miyao , Shinnosuke Takamichi

In-memory columnar databases have become mainstream over the last decade and have vastly improved the fast processing of large volumes of data through multi-core parallelism and in-memory compression thereby eliminating the usual…

Databases · Computer Science 2016-09-27 Jayanth Jayanth

Large language models (LLMs) excel across diverse natural language processing tasks but face resource demands and limited context windows. Although techniques like pruning, quantization, and token dropping can mitigate these issues, their…

Computation and Language · Computer Science 2025-08-04 Ammar Ahmed , Sheng Di , Franck Cappello , Zirui Liu , Jingoo Han , Ali Anwar

Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. However, increasingly complex tasks have revealed its disadvantages. First, a vocabulary cannot be modified once it is learned,…

Computation and Language · Computer Science 2024-08-13 Langlin Huang , Yang Feng

Recent research has highlighted the importance of dataset size in scaling language models. However, large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its…

Machine Learning · Computer Science 2023-10-10 Fuzhao Xue , Yao Fu , Wangchunshu Zhou , Zangwei Zheng , Yang You

Kaplan et al. [2020] (`Kaplan') and Hoffmann et al. [2022] (`Chinchilla') studied the scaling behavior of transformers trained on next-token language prediction. These studies produced different estimates for how the number of parameters…

Machine Learning · Computer Science 2024-11-22 Tim Pearce , Jinyeop Song

We explore a class of adversarial attacks targeting the activations of language models. By manipulating a relatively small subset of model activations, $a$, we demonstrate the ability to control the exact prediction of a significant number…

Machine Learning · Computer Science 2023-12-06 Stanislav Fort

Post-training quantization of Large Language Models (LLMs) has proven effective in reducing the memory and computational requirements for inference. In this study, we focus on a straightforward question: When aiming for a target accuracy or…

Computation and Language · Computer Science 2025-08-08 Zeyu Cao , Boyang Gu , Cheng Zhang , Pedro Gimenes , Jianqiao Lu , Jianyi Cheng , Xitong Gao , Yiren Zhao

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…

Computation and Language · Computer Science 2025-05-20 Xianglong Xu , John Bowen , Rojin Taheri

Data in biology is redundant, noisy, and sparse. How does the type and scale of available data impact model performance? In this work, we specifically investigate how protein language models (pLMs) scale with increasing pretraining data. We…

Quantitative Methods · Quantitative Biology 2025-07-31 Aviv Spinner , Erika DeBenedictis , Corey M. Hudson

With the ever-increasing volume of visual data, the efficient and lossless transmission, along with its subsequent interpretation and understanding, has become a critical bottleneck in modern information systems. The emerged codebook-based…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Yongbo Wang , Haonan Wang , Guodong Mu , Ruixin Zhang , Jiaqi Chen , Jingyun Zhang , Jun Wang , Yuan Xie , Zhizhong Zhang , Shouhong Ding

Large Language Models (LLMs) require substantial computational resources, making model compression essential for efficient deployment in constrained environments. Among the dominant compression techniques: knowledge distillation, structured…

Machine Learning · Computer Science 2025-11-26 Shivansh Chhawri , Rahul Mahadik , Suparna Rooj