training-free acceleration
- Papers
- 4
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Nov 2026
4 papers in the last two months, against 0 in the two before.
Start here
The paper to read first- 1Video AI models generate clips with 99% fewer attention computations
ESTRA accelerates video diffusion models up to 5.39× by computing only 1% of attention exactly.
Nov 2026
How fast it is moving
Often studied with
diffusion transformerA neural network architecture combining transformer layers with diffusion processes for high-quality image and video generation.3 togetherkv cache compressionReducing the size of the key-value cache in transformers via selective retention, low-rank updates, or adaptive compression.1 togethersparse attentionSelectively attending to only the most relevant positions or tokens to reduce computational overhead.1 togetherThe papers
Most central to this idea first, not most recent.
- Academiccs.LG
Fractional dynamics model speeds up diffusion transformers without extra training
FADE accelerates Diffusion Transformers by forecasting changing internal features with a fractional-dynamics model and a precomputed lookup table, maintaining quality during longer sampling skips.
Sichuan University · Nov 2026
- Research Labcs.CV
Video AI models generate clips with 99% fewer attention computations
ESTRA accelerates video diffusion models up to 5.39× by computing only 1% of attention exactly.
The University of Sydney, CSIRO · Nov 2026
- Top Universitycs.CV
BlazeVGGT speeds up VGGT 13x by selecting representative views without retraining
BlazeVGGT speeds up VGGT by 13 times on 2000 frame sequences by selecting a subset of views for attention without retraining.
University of Chinese Academy of Sciences, University of Maryland · Oct 2026
- Chinese Techcs.CV
Adaptive reference attention reuse speeds up conditioned diffusion transformers
RefAdapt-DiT adaptively reuses reference computations in diffusion transformers, achieving up to 3.54x speedup on Qwen Image Edit with comparable quality.
Tencent · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.