arXiv Machine Learning September 23, 2026 By Zijian Zhao, Dian Jin, Xialiang Tong, Sen Li, Mingxuan Yuan

Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach

Read the original on arXiv Machine Learning →

The paper introduces a lightweight evolutionary heuristic scheduler for Diffusion Large Language Models (dLLMs) that optimizes denoising trajectories using CMA-ES. It addresses failure modes of existing confidence-based schedulers—EOS Overflow and Proximal Bias—by integrating multiple heuristic features with a contextual mean-field embedding, requiring only 393 trainable parameters. Evaluations on LLaDA and Dream across reasoning and planning benchmarks show consistent outperformance over strong baselines and recent state‑of‑the‑art methods.

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 Machine Learning.

arXiv AI

Sep 3

Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models

The paper introduces PILL, a new infilling technique for diffusion language models that eliminates the need for a preset initial length and reduces inference overhead. PILL uses probing-based length-free decoding, cutting down on extra forward passes and speeding up generation. Experiments across five diffusion models and eight benchmarks show PILL outperforms the strongest baseline with higher pass rates and BLEU-2 scores while running 1.82× faster.

By Haobo Xu, Sirui Chen, Yuanchen Bei, Lingjie Chen, Yuchen Yan, Dongqi Fu, Jingrui He, Hanghang Tong

llms diffusion benchmarks

arXiv AI

Jun 3

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

arXiv:2604. 18995v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction.

By Zhenbang Du, Kejing Xia, Xinrui Zhong, Yonggan Fu, Nicolai Oswald, Binfei Ji, Brucek Khailany, Pavlo Molchanov, Yingyan Lin

llms diffusion fine-tuning efficiency

arXiv Computation and Language

3d ago

Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems

arXiv:2609.38806v1 Announce Type: cross Abstract: Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on prob...

By Woosang Jeon, Jaeyeon Kim, Sham Kakade, Yilun Du, Amrit Singh Bedi, Arun Kumar Chithanar, Chul Lee, Taehyeong Kim, Sitan Chen

llms diffusion fine-tuning

arXiv AI

Jun 2

FLARE: Diffusion for Hybrid Language Model

arXiv:2606. 01774v1 Announce Type: cross Abstract: Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment.

By Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan, Yiran Xu, Wanrong Zhu, Jason Kuen, Koustava Goswami, Rajiv Jain, Yongxin Chen, Molei Tao, Jiuxiang Gu

llms diffusion efficiency data-engineering

arXiv AI

Jun 19

Diffusion Language Models: An Experimental Analysis

arXiv:2606. 19475v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks.

By Thomas Bertolani, Davide Bucciarelli, Leonardo Zini, Marcella Cornia, Lorenzo Baraldi

llms diffusion benchmarks

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

One email a morning, machine-written

Related stories

Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems

FLARE: Diffusion for Hybrid Language Model

Diffusion Language Models: An Experimental Analysis

CAI-DLLM: Convergence Aware Inference for Diffusion Language Models