English
Related papers

Related papers: Beyond Next-Token Prediction: A Performance Charac…

200 papers

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive models for faster inference via parallel token generation. We provide a rigorous foundation for this advantage by formalizing a model of parallel…

Machine Learning · Computer Science 2026-01-01 Haozhe Jiang , Nika Haghtalab , Lijie Chen

Diffusion-based large language models (dLLMs) have shown promising performance across various reasoning tasks, establishing themselves as an alternative to autoregressive large language models (LLMs). Unlike autoregressive LLMs that…

Computation and Language · Computer Science 2026-03-02 Xiangzhong Luo , Yilin An , Zhicheng Yu , Weichen Liu , Xu Yang

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…

Computation and Language · Computer Science 2026-05-11 Georgios Batzolis , Mark Girolami , Luca Ambrogioni

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number…

Computation and Language · Computer Science 2026-03-09 Vittorio Rossi , Giacomo Cirò , Davide Beltrame , Luca Gandolfi , Paul Röttger , Dirk Hovy

Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language…

Machine Learning · Computer Science 2026-02-23 Minseo Kim , Chenfeng Xu , Coleman Hooper , Harman Singh , Ben Athiwaratkun , Ce Zhang , Kurt Keutzer , Amir Gholami

While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To…

Computation and Language · Computer Science 2026-04-14 Zhengnan Guo , Fei Tan

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Lunbin Zeng , Jingfeng Yao , Bencheng Liao , Hongyuan Tao , Wenyu Liu , Xinggang Wang

Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the…

Computation and Language · Computer Science 2026-01-19 Linhao Zhong , Linyu Wu , Bozhen Fang , Tianjian Feng , Chenchen Jing , Wen Wang , Jiaheng Zhang , Hao Chen , Chunhua Shen

We introduce the first watermark tailored for diffusion language models (DLMs), an emergent LLM paradigm able to generate tokens in arbitrary order, in contrast to standard autoregressive language models (ARLMs) which generate tokens…

Machine Learning · Computer Science 2026-02-20 Thibaud Gloaguen , Robin Staab , Nikola Jovanović , Martin Vechev

In this paper we introduce Hierarchical Diffusion Language Models (HDLM) -- a novel family of discrete diffusion models for language modeling. HDLM builds on a hierarchical vocabulary where low-level tokens with detailed semantics are…

Computation and Language · Computer Science 2025-10-13 Cai Zhou , Chenyu Wang , Dinghuai Zhang , Shangyuan Tong , Yifei Wang , Stephen Bates , Tommi Jaakkola

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Computation and Language · Computer Science 2025-11-03 Daniel Israel , Guy Van den Broeck , Aditya Grover

Diffusion-based large language models (dLLMs) have exhibited substantial potential for parallel text generation, which may enable more efficient generation compared to autoregressive models. However, current dLLMs suffer from fixed…

Computation and Language · Computer Science 2025-10-29 Yicun Yang , Cong Wang , Shaobo Wang , Zichen Wen , Biqing Qi , Hanlin Xu , Linfeng Zhang

Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast…

Computation and Language · Computer Science 2026-05-29 Jian Chen , Yesheng Liang , Zhijian Liu

Diffusion language models have emerged as a promising approach for text generation. One would naturally expect this method to be an efficient replacement for autoregressive models since multiple tokens can be sampled in parallel during each…

Machine Learning · Computer Science 2025-06-10 Guhao Feng , Yihan Geng , Jian Guan , Wei Wu , Liwei Wang , Di He

Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…

Computation and Language · Computer Science 2026-04-14 Zehua Pei , Hui-Ling Zhen , Weizhe Lin , Sinno Jialin Pan , Yunhe Wang , Mingxuan Yuan , Bei Yu

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential…

Computation and Language · Computer Science 2025-06-05 Zhepei Wei , Wei-Lin Chen , Xinyu Zhu , Yu Meng

Diffusion Large Language Models (DLLMs) have emerged as a powerful alternative to autoregressive models, enabling parallel token generation across multiple positions. However, preference alignment of DLLMs remains challenging due to high…

Computation and Language · Computer Science 2026-02-04 Liang Lin , Feng Xiong , Zengbin Wang , Kun Wang , Junhao Dong , Xuecai Hu , Yong Wang , Xiangxiang Chu

Large language model (LLM)-based embedding models, benefiting from large scale pre-training and post-training, have begun to surpass BERT and T5-based models on general-purpose text embedding tasks such as document retrieval. However, a…

Computation and Language · Computer Science 2025-05-22 Siyue Zhang , Yilun Zhao , Liyuan Geng , Arman Cohan , Anh Tuan Luu , Chen Zhao

Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirectional context modeling. However, harnessing this flexibility…

Computation and Language · Computer Science 2026-05-28 Jiyeon Kim , Sungik Choi , Yongrae Jo , Moontae Lee , Minjoon Seo

Recently, Diffusion Large Language Models (DLLMs) have offered high throughput and effective sequential reasoning, making them a competitive alternative to autoregressive LLMs (ALLMs). However, parallel decoding, which enables simultaneous…

Computation and Language · Computer Science 2025-10-13 Qiguang Chen , Hanjing Li , Libo Qin , Dengyun Peng , Jinhao Liu , Jiangyi Wang , Chengyue Wu , Xie Chen , Yantao Du , Wanxiang Che