arXiv:2608. 06628v1 Announce Type: new Abstract: Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding.
By Jinha Kim, Younghun Roh, Jaeyeon Kim
arXiv:2606.10537v2 Announce Type: replace
Abstract: Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales
quadratically with...
By Jing Xiong, Qi Han, Shansan Gong, Yunta Hsieh, Boyuan Zheng, Chengyue Wu, Chaofan Tao, Chenyang Zhao, Ngai Wong
DRAMA is a training‑free acceleration framework for multimodal diffusion large language models that dissects attention redundancy by probing attention tensors along spatial and temporal axes. It identifies two key redundancy patterns: a sparse subset of visual tokens consistently receives most attention, and attention distributions stabilize quickly after an initial phase. Leveraging these insights, DRAMA introduces Spatial‑Redundancy‑Aware Visual Token Pruning and Sufficiency‑Guided Adaptive Stopping, achieving an average 18.67× inference speedup across six vision‑language benchmarks while preserving competitive accuracy.
By Yi-Hsin Hung, Fangfu Liu, Shao-Yuan Lo, Chu-Song Chen
Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with context length and becomes prohibitive for long-context scenarios. We propose Prefilling-dLLM, a training-free prefill-decode disaggregation framework for dLLMs that partitions the prefix into N chunks, caches their KV representations once, and selects the top-K most relevant chunks with intra-chunk token sparsity for decoding, showing that sparse prefilling can outperform dense attention while reducing per-step complexity from quadratic in the full sequence length to quadratic only in the decode length.
arXiv:2610.31911v1 Announce Type: new
Abstract: As large language models (LLMs) process increasingly long sequences, attention becomes a major computational bottleneck. Sparse attention mostly target...
By Keqi Deng, Ruchao Fan, Jinyu Li
Prism Attention introduces a proposal‑refined sparse attention framework that replaces static cross‑layer index reuse with a coarse‑to‑fine strategy, allowing layer‑wise adaptability while maintaining efficiency. The method leverages the observation that high‑attention tokens remain largely stable across layers, with changes concentrated near the boundary of previously selected regions. Experiments demonstrate state‑of‑the‑art performance on reasoning and long‑context benchmarks, achieving a 3.4× decoding speedup over FlashAttention at 128K context length.
By Zhenxu Tian, Kebin Liu, Zhengwu Yang, Yi Su, Qingqing Dang, Yanlin Sha, Kaipeng Deng, Dianhai Yu, Yanjun Ma, Juntao Li, Min Zhang
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
Prefilling-dLLM v2 is a diffusion language model that learns to route computation using a native mask token, enabling efficient sparse attention across long contexts. By appending a mask at the end of each chunk and using a learned role offset, the model selectively attends to top‑K chunks every fourth layer while maintaining local windows elsewhere. Evaluated on 16K–128K contexts, Prefilling-dLLM v2 outperforms other sparse methods (NSA, DSA, SWA) on RULER tasks and achieves a 172× speedup over full dense attention at 128K tokens.
DUET is a training‑free dual‑sparse inference framework for diffusion language models that reduces inference cost by two techniques: prefix Key‑Value sparsity and early query sparsity. It constructs a compact historical KV subset reused across denoising steps, and predicts which positions will be updated to propagate only the necessary queries through the suffix Transformer layers. Experiments demonstrate that DUET keeps accuracy while delivering up to 4.72× speedups on large models with 32K context length.
By Siyuan Yan, Shen Gu, Xiaoxing Ma, Chun Cao, Jingwei Xu
arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.
By Zhiyuan Liu, Yicun Yang, Yaojie Zhang, Junjie Chen, Chang Zou, Qingyuan Wei, Shaobo Wang, Yichen Zhu, Linfeng Zhang
arXiv:2603. 08026v2 Announce Type: replace-cross Abstract: Masked diffusion language models enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation.
By Younjoo Lee, Seungkyun Dan, Junghoo Lee, Jaiyoung Park, Jung Ho Ahn
arXiv:2610.04753v2 Announce Type: replace-cross
Abstract: Autoregressive generation in Large Language Models (LLMs) is constrained by the memory and computational demands of attention mechanisms. Spa...
By Noam Elata, Itay Lamprecht, Mikey Shechter, Daniel Ohayon, Itay Hubara, Daniel Soudry