English
Related papers

Related papers: Local and Global Decoding in Text Generation

200 papers

Diffusion models have revolutionized image generation in recent years, yet they are still limited to a few sizes and aspect ratios. We propose ElasticDiffusion, a novel training-free decoding method that enables pretrained text-to-image…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Moayed Haji-Ali , Guha Balakrishnan , Vicente Ordonez

As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance in synthesizing complicated data distributions through a denoising process gradually guided…

Machine Learning · Computer Science 2026-04-23 Fangjun Hu , Guangkuo Liu , Yifan F. Zhang , Xun Gao

The importance of neighborhood construction in local explanation methods has been already highlighted in the literature. And several attempts have been made to improve neighborhood quality for high-dimensional data, for example, texts, by…

Computation and Language · Computer Science 2023-02-16 Yi Cai , Arthur Zimek , Eirini Ntoutsi , Gerhard Wunder

Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it…

Computation and Language · Computer Science 2021-06-03 Paras Bhatt , Anthony Rios

One of the latest applications of Artificial Intelligence (AI) is to generate images from natural language descriptions. These generators are now becoming available and achieve impressive results that have been used for example in the front…

Computation and Language · Computer Science 2022-11-18 Pedro Reviriego , Elena Merino-Gómez

MCMC algorithms such as Metropolis-Hastings algorithms are slowed down by the computation of complex target distributions as exemplified by huge datasets. We offer in this paper a useful generalisation of the Delayed Acceptance approach,…

Computation · Statistics 2015-03-06 Marco Banterle , Clara Grazian , Anthony Lee , Christian P. Robert

The state-of-the-art error correcting codes are based on large random constructions (random graphs, random permutations, ...) and are decoded by linear-time iterative algorithms. Because of these features, they are remarkable examples of…

Disordered Systems and Neural Networks · Physics 2016-08-31 Silvio Franz , Michele Leone , Andrea Montanari , Federico Ricci-Tersenghi

Diffusion models have demonstrated their capability to synthesize high-quality and diverse images from textual prompts. However, simultaneous control over both global contexts (e.g., object layouts and interactions) and local details (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-25 Moyuru Yamada

This paper proposes a new "decompose-and-edit" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generation. In the proposed paradigm, global and local factors in…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-29 Dacheng Yin , Chuanxin Tang , Yanqing Liu , Xiaoqiang Wang , Zhiyuan Zhao , Yucheng Zhao , Zhiwei Xiong , Sheng Zhao , Chong Luo

We propose a decentralised "local2global" approach to graph representation learning, that one can a-priori use to scale any embedding technique. Our local2global approach proceeds by first dividing the input graph into overlapping subgraphs…

Machine Learning · Computer Science 2021-07-27 Lucas G. S. Jeub , Giovanni Colavizza , Xiaowen Dong , Marya Bazzi , Mihai Cucuringu

Diffusion large language models (dLLMs) theoretically permit token decoding in arbitrary order, a flexibility that could enable richer exploration of reasoning paths than autoregressive (AR) LLMs. In practice, however, random-order decoding…

Computation and Language · Computer Science 2026-04-02 Liancheng Fang , Aiwei Liu , Henry Peng Zou , Yankai Chen , Enze Ma , Leyi Pan , Chunyu Miao , Wei-Chieh Huang , Xue Liu , Philip S. Yu

The gap between the known randomized and deterministic local distributed algorithms underlies arguably the most fundamental and central open question in distributed graph algorithms. In this paper, we develop a generic and clean recipe for…

Data Structures and Algorithms · Computer Science 2019-09-19 Mohsen Ghaffari , David G. Harris , Fabian Kuhn

Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays an important role in determining the quality of their…

Machine Learning · Computer Science 2026-03-03 Haojin Yang , Rui Hu , Zequn Sun , Rui Zhou , Yujun Cai , Yiwei Wang

Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday life. One common approach uses energy-based decoding, which…

Computation and Language · Computer Science 2025-02-07 Patrick Pynadath , Ruqi Zhang

How do two distributions of texts differ? Humans are slow at answering this, since discovering patterns might require tediously reading through hundreds of samples. We propose to automatically summarize the differences by "learning a…

Computation and Language · Computer Science 2022-05-19 Ruiqi Zhong , Charlie Snell , Dan Klein , Jacob Steinhardt

The ability to reliably distinguish human-written text from that generated by large language models is of profound societal importance. The dominant approach to this problem exploits the likelihood hypothesis: that machine-generated text…

Computation and Language · Computer Science 2026-05-08 Tom Kempton , Viktor Drobnyi , Maeve Madigan , Stuart Burrell

We investigate the use of the Metropolis-Hastings algorithm to sample posterior distribution in a Bayesian inverse problem, where the likelihood function is random. Concretely, we consider the case where one has full field observations of a…

Numerical Analysis · Mathematics 2026-02-20 Emil Løvbak , Sebastian Krumscheid

Modern language models operate on subword-tokenized text in order to make a trade-off between model size, inference speed, and vocabulary coverage. A side effect of this is that, during inference, models are evaluated by measuring the…

Computation and Language · Computer Science 2025-10-24 David Pohl , Marco Cognetta , Junyoung Lee , Naoaki Okazaki

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

Software Engineering · Computer Science 2026-02-10 Viacheslav Siniaev , Iaroslav Chelombitko , Aleksey Komissarov

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice,…

Computation and Language · Computer Science 2015-03-02 Jiajun Zhang