The paper investigates how block‑diffusion language models can use a constant‑size cache to enable efficient parallel decoding. By employing sequence mixers that summarize completed blocks into a reusable state and a block‑causal training objective, the authors pretrain three 3B block‑diffusion denoisers (attention, Mamba, and hybrid) on 300 B tokens. The resulting state‑space cache remains O(1) in memory and latency regardless of context length, yielding significant speed‑up and memory savings compared to traditional attention‑based caches, especially at very long sequences.
By Vaibhav Singh, Pierre-Andr\'e No\"el, Torsten Scholak, Eugene Belilovsky, Oleksiy Ostapenko
SoftCache introduces an adaptive step size caching mechanism for diffusion transformers, replacing hard binary caching with a soft approach that uses a headroom signal to determine how far cached steps advance. By allowing steps to jump beyond scheduled nodes and shrink as a refresh nears, SoftCache achieves significant speedups—between 3.5× and 6.9×—across image and video models such as FLUX, HunyuanVideo, and Wan2.1, outperforming all baselines on four fidelity metrics.
By Shimon Malnick, Nadav Orenstein, Ohad Fried, Shai Avidan
Masked diffusion language models (dLLMs) promise faster text generation by denoising multiple tokens simultaneously, yet their real‑world serving behavior has been largely unexamined. Using LLaDA‑8B‑Instruct on a single NVIDIA H200 GPU, the study finds that request difficulty is discretized into 11 step‑count levels, short‑budget benchmarks underestimate serving variance, and only 24% of single‑request time is GPU computation, with batching mainly reducing CPU dispatch overhead. The authors also demonstrate that output quality remains stable across batch sizes and propose a batch‑timeout rule for synchronized batching under Poisson arrivals.
By Farhana Amin, Sabiha Afroz, Mona Moghadampanah, Dimitrios S. Nikolopoulos
arXiv:2607. 27842v1 Announce Type: cross Abstract: Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive.
By Hanshuai Cui, Zhiqing Tang, Zhi Yao, Qianli Ma, Fanshuai Meng, Weijia Jia
arXiv:2609.32540v2 Announce Type: replace-cross
Abstract: Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, eac...
By Yikai Wang, Xiao Han, Mengmeng Xu, Juan Camilo Perez, Yiannis Douratsos, Sen He, Zijian Zhou, Fei Zhang, Zhaochong An, Juan-Manuel Perez-Rua, Chen Change Loy, Tao Xiang
arXiv:2607. 12121v1 Announce Type: cross Abstract: Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge.
By Yaqi Qiao, Ping He, Songrun Xie, Ayush Barik, Chensong Zhang, Zhengzhong Tu, Fan Lai