English
Related papers

Related papers: Text Generation Beyond Discrete Token Sampling

200 papers

Data-to-text (D2T) generation is the task of generating texts from structured inputs. We observed that when the same target sentence was repeated twice, Transformer (T5) based model generates an output made up of asymmetric sentences from…

Computation and Language · Computer Science 2022-08-10 Choonghan Kim , Gary Geunbae Lee

As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requiring thousands of model forward passes to generate a single…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Yao Teng , Fuyun Wang , Xian Liu , Zhekai Chen , Han Shi , Yu Wang , Zhenguo Li , Weiyang Liu , Difan Zou , Xihui Liu

Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e.,…

Computation and Language · Computer Science 2020-07-02 Boyuan Pan , Yazheng Yang , Kaizhao Liang , Bhavya Kailkhura , Zhongming Jin , Xian-Sheng Hua , Deng Cai , Bo Li

Non-autoregressive (NAR) text generation has attracted much attention in the field of natural language processing, which greatly reduces the inference latency but has to sacrifice the generation accuracy. Recently, diffusion models, a class…

Computation and Language · Computer Science 2023-05-16 Yifan Li , Kun Zhou , Wayne Xin Zhao , Ji-Rong Wen

Recent work has shown that energy-based language modeling is an effective framework for controllable text generation because it enables flexible integration of arbitrary discriminators. However, because energy-based LMs are globally…

Computation and Language · Computer Science 2023-12-08 Jarad Forristal , Niloofar Mireshghallah , Greg Durrett , Taylor Berg-Kirkpatrick

Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their…

Computation and Language · Computer Science 2022-10-24 Robin M. Schmidt , Telmo Pires , Stephan Peitz , Jonas Lööf

Diffusion models have demonstrated significant potential in achieving state-of-the-art performance across various text generation tasks. In this systematic study, we investigate their application to the table-to-text problem by adapting the…

Computation and Language · Computer Science 2024-09-24 Aleksei S. Krylov , Oleg D. Somov

Autoregressive large language models (LLMs) generate text token-by-token, requiring n forward passes to produce a sequence of length n. Recent work, Exploring the Latent Capacity of LLMs for One-Step Text Reconstruction (Mezentsev and…

Machine Learning · Computer Science 2026-02-23 Ivan Bondarenko , Egor Palkin , Fedor Tikunov

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Ning Zhang , Zhengyu Li , Kwong Weng Loh , Mingxi Xu , Qi Wang , Zhengyu Wen , Xiaoyu He , Wei Zhao , Kehong Gong , Mingyuan Zhang

Recent work has framed constrained text generation with autoregressive language models as a probabilistic inference problem. Among these, Zhao et al. (2024) introduced a promising approach based on twisted Sequential Monte Carlo, which…

Machine Learning · Computer Science 2025-11-26 Sooyeon Kim , Giung Nam , Byoungwoo Park , Juho Lee

The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer…

Machine Learning · Computer Science 2024-11-05 Cheng Yang , Yang Sui , Jinqi Xiao , Lingyi Huang , Yu Gong , Yuanlin Duan , Wenqi Jia , Miao Yin , Yu Cheng , Bo Yuan

The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. From a distributional view, MLE in fact minimizes the Kullback-Leibler divergence (KLD) between the distribution of the…

Computation and Language · Computer Science 2023-02-28 Haozhe Ji , Pei Ke , Zhipeng Hu , Rongsheng Zhang , Minlie Huang

This paper presents a systematic survey on recent development of neural text generation models. Specifically, we start from recurrent neural network language models with the traditional maximum likelihood estimation training scheme and…

Computation and Language · Computer Science 2018-03-21 Sidi Lu , Yaoming Zhu , Weinan Zhang , Jun Wang , Yong Yu

Recently, many text-to-image diffusion models have excelled at generating high-resolution images from text but struggle with precise control over spatial composition and object counting. To address these challenges, prior works have…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Huancheng Chen , Jingtao Li , Weiming Zhuang , Haris Vikalo , Lingjuan Lyu

The autoregressive language model (ALM) trained with maximum likelihood estimation (MLE) is widely used in unconditional text generation. Due to exposure bias, the generated texts still suffer from low quality and diversity. This presents…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Xingyuan Chen , Ping Cai , Peng Jin , Hongjun Wang , Xinyu Dai , Jiajun Chen

We present Bayesian Mixture of Experts (Bayesian-MoE), a post-hoc uncertainty estimation framework for fine-tuned large language models (LLMs) based on Mixture-of-Experts architectures. Our method applies a structured Laplace approximation…

Machine Learning · Computer Science 2025-11-13 Maryam Dialameh , Hossein Rajabzadeh , Weiwei Zhang , Walid Ahmed , Hyock Ju Kwon

We develop a multivariate posterior sampling procedure through deep generative quantile learning. Simulation proceeds implicitly through a push-forward mapping that can transform i.i.d. random vector samples from the posterior. We utilize…

Computation · Statistics 2025-05-01 Jungeum Kim , Percy S. Zhai , Veronika Ročková

Large language models (LLMs) have enabled the development of numerous specialized, task-specific variants. However, the maintenance and deployment of these individual models present substantial challenges in terms of resource utilization…

Machine Learning · Computer Science 2024-11-04 Quy-Anh Dang , Chris Ngo

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models…

Computation and Language · Computer Science 2020-05-12 Xiang Lisa Li , Alexander M. Rush

Despite the crucial importance of accelerating text generation in large language models (LLMs) for efficiently producing content, the sequential nature of this process often leads to high inference latency, posing challenges for real-time…

Computation and Language · Computer Science 2024-05-27 Mahsa Khoshnoodi , Vinija Jain , Mingye Gao , Malavika Srikanth , Aman Chadha