English
Related papers

Related papers: Parallel Token Prediction for Language Models

200 papers

Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per…

Machine Learning · Computer Science 2026-05-20 Yufeng Xu , Zishuo Bao , Qian Wang , Zeshen Zhang , Haoqi Zhang , Bowen Peng , Ang Li , Rahul Chalamala , Yucheng Lu

The autoregressive nature of large language models (LLMs) fundamentally limits inference speed, as each forward pass generates only a single token and is often bottlenecked by memory bandwidth. Speculative decoding has emerged as a…

Machine Learning · Computer Science 2025-12-02 Zihao An , Huajun Bai , Ziqiong Liu , Dong Li , Emad Barsoum

Language model (LM) decoding is based on the next-token prediction (NTP) probability distribution. For neural LMs (e.g., Transformer-based), NTP distribution is essentially a softmax-regularized dot product between an encoded input context…

Computation and Language · Computer Science 2024-10-04 Letian Peng , Chenyang An , Jingbo Shang

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by…

Computation and Language · Computer Science 2025-11-20 Xueying Ding , Xingyue Huang , Mingxuan Ju , Liam Collins , Yozen Liu , Leman Akoglu , Neil Shah , Tong Zhao

Motivated by the success of Transformers when applied to sequences of discrete symbols, token-based world models (TBWMs) were recently proposed as sample-efficient methods. In TBWMs, the world model consumes agent experience as a…

Machine Learning · Computer Science 2024-05-30 Lior Cohen , Kaixin Wang , Bingyi Kang , Shie Mannor

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Computation and Language · Computer Science 2024-05-24 Yufan Jiang , Qiaozhi He , Xiaomin Zhuang , Zhihua Wu , Kunpeng Wang , Wenlai Zhao , Guangwen Yang

Transformer-based models primarily rely on Next Token Prediction (NTP), which predicts the next token in a sequence based on the preceding context. However, NTP's focus on single-token prediction often limits a model's ability to plan ahead…

Computation and Language · Computer Science 2025-08-12 Charlie Wyatt , Aditya Joshi , Flora Salim

Humans ponder before articulating complex sentence elements, enabling deeper cognitive processing through focused effort. In this work, we introduce this pondering process into language models by repeatedly invoking the forward process…

Computation and Language · Computer Science 2026-02-23 Boyi Zeng , Shixiang Song , Siyuan Huang , Yixuan Wang , He Li , Ziwei He , Xinbing Wang , Zhiyu Li , Zhouhan Lin

Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervision, Multi-Token Prediction (MTP) has shown promise in…

Machine Learning · Computer Science 2026-04-21 Qimin Zhong , Hao Liao , Haiming Qin , Mingyang Zhou , Rui Mao , Wei Chen , Naipeng Chao

Optimizing training performance in large language models (LLMs) remains an essential challenge, particularly in improving model performance while maintaining computational costs. This work challenges the conventional approach of training…

Computation and Language · Computer Science 2025-11-04 Chun-Hao Yang , Bo-Han Feng , Tzu-Yuan Lai , Yan Yu Chen , Yin-Kai Dean Huang , Shou-De Lin

Traditional language models operate autoregressively, i.e., they predict one token at a time. Rapid explosion in model sizes has resulted in high inference times. In this work, we propose DynaMo, a suite of multi-token prediction language…

Computation and Language · Computer Science 2024-05-03 Shikhar Tuli , Chi-Heng Lin , Yen-Chang Hsu , Niraj K. Jha , Yilin Shen , Hongxia Jin

Large Language Models (LLMs) have achieved impressive performance across diverse tasks but continue to struggle with learning transitive relations, a cornerstone for complex planning. To address this issue, we investigate the Multi-Token…

Artificial Intelligence · Computer Science 2025-09-30 Qimin Zhong , Hao Liao , Siwei Wang , Mingyang Zhou , Xiaoqun Wu , Rui Mao , Wei Chen

Since the inception of Large Language Models (LLMs), the quest to efficiently train them for superior reasoning capabilities has been a pivotal challenge. The dominant training paradigm for LLMs is based on next token prediction (NTP).…

Computation and Language · Computer Science 2025-02-21 Pengxiao Lin , Zhongwang Zhang , Zhi-Qin John Xu

Current soft prompt methods yield limited performance when applied to small-sized models (fewer than a billion parameters). Deep prompt-tuning, which entails prepending parameters in each layer for enhanced efficacy, presents a solution for…

Computation and Language · Computer Science 2024-04-02 Mingqi Li , Feng Luo

Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explores an alternative axis: increasing per-token computation…

Computation and Language · Computer Science 2026-03-11 Boyi Zeng , Yiqin Hao , He Li , Shixiang Song , Feichen Song , Zitong Wang , Siyuan Huang , Yi Xu , ZiWei He , Xinbing Wang , Zhouhan Lin

We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of…

Computation and Language · Computer Science 2023-02-03 Charlie Chen , Sebastian Borgeaud , Geoffrey Irving , Jean-Baptiste Lespiau , Laurent Sifre , John Jumper

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a…

Computation and Language · Computer Science 2024-01-15 Sen Yang , Shujian Huang , Xinyu Dai , Jiajun Chen

Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented…

Sound · Computer Science 2020-10-23 Isaac Elias , Heiga Zen , Jonathan Shen , Yu Zhang , Ye Jia , Ron Weiss , Yonghui Wu

Dynamic graphs serve as a generic abstraction and description of the evolutionary behaviors of various complex systems (e.g., social networks and communication networks). Temporal link prediction (TLP) is a classic yet challenging inference…

Social and Information Networks · Computer Science 2023-06-30 Meng Qin , Dit-Yan Yeung