arXiv Computation and Language September 23, 2026 By Xiaocheng Lu, Shuhan Guo, Ziyue Ma, Jie Zhang, Jian Liu, Jingcai Guo, Haoxuan Che, Song Guo

PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models

Read the original on arXiv Computation and Language →

The paper introduces PACE-dLLM, an acceleration method for diffusion language models (dLLMs) that uses the model’s own per‑step confidence to estimate a ‘confidence cliff’ and determine the optimal look‑ahead horizon for block decoding. By fitting this cliff in closed form at each step, PACE-dLLM sets the horizon to its saturation point and applies an independent confidence threshold for token commitment, thereby avoiding the trade‑offs inherent in fixed‑size block decoding. Experiments on reasoning and code benchmarks show that PACE-dLLM achieves the best average accuracy on open‑source dLLM backbones while delivering significant wall‑clock speedups—up to 5.23× on LLaDA and 3.06× on Dream—improving the quality‑throughput Pareto frontier.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Aug 25

CAI-DLLM: Convergence Aware Inference for Diffusion Language Models

arXiv:2608.22646v1 Announce Type: new Abstract: Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation...

By Farhana Amin, Sabiha Afroz, Dimitrios S. Nikolopoulos

llms diffusion benchmarks

arXiv AI

Jun 2

SimSD: Simple Speculative Decoding in Diffusion Language Models

arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.

By Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo, Jinya Jiang, Haoru Li, Chaojie Ren, Yiming Huang, Kaijie Zhu, Zhongkai Yu, Kun Zhou, Jingbo Shang

llms diffusion efficiency benchmarks

arXiv AI

Jun 3

Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference

arXiv:2606. 02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.

By Siva Rajesh Kasa, Yasong Dai, Sumit Negi, Hongdong Li

llms diffusion efficiency benchmarks

arXiv AI

Aug 14

Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models

arXiv:2607. 28166v2 Announce Type: replace-cross Abstract: Diffusion language models expose a provisional prediction at every denoising step, and on many tasks the candidate answer inside it stabilizes before the step schedule is exhausted.

By Chia-Ming Lee, Shao-Kai Liu, Ming-Ching Chang, Xin Li, Yu-Lun Liu, Chih-Chung Hsu

llms diffusion

arXiv AI

Aug 13

CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

arXiv:2608. 11235v1 Announce Type: new Abstract: Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon.

By Yifan Wu, Yufeng Zhang, Kenli Li

llms diffusion benchmarks

arXiv Machine Learning

Sep 4

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

arXiv:2609. 04010v1 Announce Type: new Abstract: Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation.

By Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham, Jonathan Geuter, Chaitanya Dwivedi, Varad Pimpalkhute, Yash Akhauri, Alexander Moreno, Mikhail Yurochkin, Zhenting Wang, Mostafa Elhoushi, Nolan Dey, Shane Bergsma, Joel Hestness, John Thickstun, Eric Xing, Zhengzhong Liu

llms agents diffusion efficiency benchmarks

One email a morning, machine-written

Related stories

CAI-DLLM: Convergence Aware Inference for Diffusion Language Models

SimSD: Simple Speculative Decoding in Diffusion Language Models

Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference

Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models

CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

Unlocking Lossless Speedups in LLMs via Discrete Diffusion