English
Related papers

Related papers: Lazy-k: Decoding for Constrained Token Classificat…

200 papers

A likelihood encoder is studied in the context of lossy source compression. The analysis of the likelihood encoder is based on the soft-covering lemma. It is demonstrated that the use of a likelihood encoder together with the soft-covering…

Information Theory · Computer Science 2016-04-07 Eva C. Song , Paul Cuff , H. Vincent Poor

Recent results in compressed sensing showed that the optimal subsampling strategy should take into account the sparsity pattern of the signal at hand. This oracle-like knowledge, even though desirable, nevertheless remains elusive in most…

Information Theory · Computer Science 2023-06-28 Simon Ruetz

Due to the fundamental connection between next-symbol prediction and compression, modern predictive models, such as large language models (LLMs), can be combined with entropy coding to achieve compression rates that surpass those of…

Information Theory · Computer Science 2026-01-27 Cordelia Hu , Jennifer Tang

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

Machine Learning · Computer Science 2022-02-09 Chidubem Arachie , Bert Huang

Large Language Models (LLMs) can exhibit considerable variation in the quality of their sampled outputs. Reranking and selecting the best generation from the sampled set is a popular way of obtaining strong gains in generation quality. In…

Artificial Intelligence · Computer Science 2024-01-15 Siddhartha Jain , Xiaofei Ma , Anoop Deoras , Bing Xiang

A key challenge in machine learning is to design interpretable models that can reduce their inputs to the best subset for making transparent predictions, especially in the clinical domain. In this work, we propose a certifiably optimal…

Artificial Intelligence · Computer Science 2023-10-10 Ricardo Knauer , Erik Rodner

Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained models assign high probability to plausible sequences given the…

Computation and Language · Computer Science 2022-10-04 Yao Zhao , Misha Khalman , Rishabh Joshi , Shashi Narayan , Mohammad Saleh , Peter J. Liu

Chase-like decoding algorithms are a popular choice for soft-input decoding of algebraic codes. In this paper, we evaluate the performance of different test pattern sets using three methods. For test pattern sets with a certain structure…

Information Theory · Computer Science 2026-05-12 Tim Janz , Simon Obermüller , Andreas Zunker , Stephan ten Brink

Solving chance-constrained stochastic optimal control problems is a significant challenge in control. This is because no analytical solutions exist for up to a handful of special cases. A common and computationally efficient approach for…

Systems and Control · Electrical Eng. & Systems 2023-10-05 Alexandre Capone , Tim Brüdigam , Sandra Hirche

Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can…

Computation and Language · Computer Science 2026-03-13 Amirhossein Bozorgkhoo , Igor Molybog

Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recent generative ranking methods enable listwise optimization…

Information Retrieval · Computer Science 2026-03-05 Chenfei Li , Hantao Zhao , Weixi Yao , Ruiming Huang , Rongrong Lu , Geng Tian , Dongying Kong

Code generation under long contexts is becoming increasingly critical as Large Language Models (LLMs) are required to reason over extensive information in the codebase. While recent advances enable code LLMs to process long inputs, high API…

Computation and Language · Computer Science 2025-10-02 Yuling Shi , Yichun Qian , Hongyu Zhang , Beijun Shen , Xiaodong Gu

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…

Computation and Language · Computer Science 2025-03-06 Guofeng Quan , Wenfeng Feng , Chuzhan Hao , Guochao Jiang , Yuewei Zhang , Hao Wang

Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks.…

Sound · Computer Science 2025-08-18 Kentaro Onda , Satoru Fukayama , Daisuke Saito , Nobuaki Minematsu

Language models can largely benefit from efficient tokenization. However, they still mostly utilize the classical BPE algorithm, a simple and reliable method. This has been shown to cause such issues as under-trained tokens and sub-optimal…

Computation and Language · Computer Science 2024-09-10 Pavel Chizhov , Catherine Arnett , Elizaveta Korotkova , Ivan P. Yamshchikov

In this paper, we compare various methods to compress a text using a neural model. We find that extracting tokens as latent variables significantly outperforms the state-of-the-art discrete latent variable models such as VQ-VAE.…

Computation and Language · Computer Science 2019-01-28 Aran Komatsuzaki

Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from…

Machine Learning · Computer Science 2013-01-30 Thomas Hofmann

Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation. However, in practice, it…

Computation and Language · Computer Science 2024-06-14 Siqi Kou , Lanxiang Hu , Zhezhi He , Zhijie Deng , Hao Zhang

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision…

Computation and Language · Computer Science 2022-05-16 Ziqian Zeng , Weimin Ni , Tianqing Fang , Xiang Li , Xinran Zhao , Yangqiu Song

This paper describes a revision of the classic Lazy Probabilistic Roadmaps algorithm (Lazy PRM), that results from pairing PRM and a novel Branch-and-Cut (BC) algorithm. Cuts are dynamically generated constraints that are imposed on minimum…

Robotics · Computer Science 2022-09-30 Miquel Ramirez , Daniel Selvaratnam , Chris Manzie
‹ Prev 1 8 9 10 Next ›