paper-with-me

Papers

BAG: Budget-Aware Gating for Diffusion Caching

2026-08-10 · Tong Zhao, Mingkun Lei, Yucheng Han, Chi Zhang arxiv

Diffusion caching is a lightweight strategy that accelerates Diffusion Transformers (DiTs) by reusing intermediate features across denoising steps, but existing paradigms face a fundamental trade-off: online heuristics lack global budget awareness, whereas static schedules lack instance adaptivity and fail to flexibly adapt to varying runtime budget constraints. To bridge this gap, we present BAG (Budget-Aware Gating), a novel caching policy that unifies global budget pacing with dynamic, instance-adaptive feature reuse. Rather than relying on hand-crafted rules, BAG employs a lightweight gating network that dynamically decides whether to execute a full computation or reuse cached features at each step by jointly conditioning on the budget state and local trajectory feedback. We train this policy via offline-to-online schedule distillation, transferring the decision-making of offline-searched schedules into a compact online gate. Extensive experiments on FLUX.1-dev, Wan2.1, and Qwen-Image-2512 demonstrate that BAG consistently outperforms state-of-the-art caching methods across various speedup tiers while remaining robust across different resolutions, seeds, and guidance scales. Code will be released.

📄 PDF Abstract BibTeX arXiv:2608.09231

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models

2026-06-30 · Huanlin Gao, Fang Zhao, Qiang Hui, Fuyuan Shi 외 arxiv

We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives,…

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

2026-02-27 · Yasaman Haghighi, Alexandre Alahi arxiv

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerati…

Video Generation

Budget-Constrained Step-Level Diffusion Caching

2026-06-11 · Mingkun Lei, Tong Zhao, Liangyu Yuan, Chi Zhang arxiv

Step-level caching accelerates diffusion models by exploiting temporal redundancy across denoising steps. Existing methods make per-step cache decisions using threshold-based heuristics, without directly optimizing for f…

Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers

2026-03-05 · Guandong Li arxiv

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing …

Video Generation

ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE

2026-06-04 · Mishan Aliev, Eva Neudachina, Ilya Bykov, Aleksandr Oganov 외 arxiv

Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or predicting intermediate activations acr…