arXiv Computer Vision August 24, 2026 By Yangshuai Liu, Zheming Li, Jiaao Li, Kang He, Ziliang Lai, Zhitai Liu, Chengru Song

Anchoring Instruction Outside Mask: Exact Reference Caching for Efficient In-Context Diffusion Transformers

Read the original on arXiv Computer Vision →

The Flow has not summarised this story yet — read it at arXiv Computer Vision.

arXiv Computer Vision

Sep 25

Beyond Attention Masks: Instruction Anchoring for Efficient In-Context Diffusion Generation

The paper introduces AnchorCache, a parameter‑free token‑layout and attention‑mask design that decouples reference tokens from the target in in‑context diffusion transformers. By inserting static text anchors, the method conditions reference representations on the instruction during cache construction, enabling exact key‑value reuse across denoising steps. To restore quality lost by this structural change, the authors employ teacher‑forced velocity distillation followed by a brief on‑policy stage, achieving full‑attention quality while delivering up to 6.40× speedup in diffusion transformer inference across image, speech, and video benchmarks.

By Yangshuai Liu, Zheming Li, Jiaao Li, Kang He, Ziliang Lai, Zhitai Liu, Chengru Song

llms diffusion efficiency benchmarks

arXiv Computer Vision

Oct 27

Copying As Defense: Protecting Images from Editing By Eliciting Model Copying

arXiv:2610.35566v1 Announce Type: new Abstract: Image editors built on diffusion transformers (DiTs), such as Flux Kontext, make it possible to turn a single photograph into a convincing manipulated...

By Salma Abdel Magid, Sanghyuk Chun, Eric Slyman, Kushal Kafle, Olga Russakovsky

llms diffusion benchmarks

arXiv AI

Oct 27

ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing

ToDoPro introduces an early token‑reduction strategy for reference‑based image generation that uses a few denoising steps on 2× downsampled reference images to probe token importance with the existing Diffusion Transformer. Tokens are then hierarchically pruned: low‑importance tokens are discarded, mid‑importance tokens are replaced by their downsampled versions, and high‑importance tokens are retained. Experiments on three base models and two benchmarks show significant inference speedups, reduced peak GPU memory, and improved generation quality by filtering out noisy reference tokens.

By Caiyi Sun, Yujing Sun, Siu-Ming Yiu

llms diffusion benchmarks

arXiv Machine Learning

Oct 7

RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing

arXiv:2610.07720v1 Announce Type: cross Abstract: Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existin...

By Wanning He, Yuyao Zhang, Yu-Wing Tai

llms diffusion fine-tuning benchmarks

arXiv AI

Jul 7

FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion

arXiv:2602. 05305v3 Announce Type: replace-cross Abstract: Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models.

By Zhuokun Chen, Jianfei Cai, Bohan Zhuang

llms diffusion efficiency

Hugging Face Trending Papers

Jun 22

Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping

Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis. However, these models are computationally expensive in runtime, and their cost scales severely with the number of input references.

diffusion fine-tuning efficiency