
HL
Haosen Li, Wenshuo Chen, Shaofeng Liang, Lei Wang, Bowen Tian, Yutao Yue
· 1 min read
ResearcharXiv cs.CV
GeoShrink: Accelerating Diffusion Transformers with Two Lines of Code
arXiv:2609.33723v1 Announce Type: new
Abstract: Diffusion transformers incur substantial inference cost through repeated model evaluations along a sampling trajectory. We introduce GeoShrink, a training-free acceleration method that retains the original solver grid while evaluating the model only at a prescribed set of anchors. At skipped stages, GeoShrink predicts the solver-facing output by adding a geometrically retained fraction of the latest observed innovation to the most recent exact output. We derive this rule from chordal tangent transport and round-trip line projection, and establish a geometric anchor-spacing principle that minimizes the largest adjacent gap expansion under fixed coverage and first span. The analysis characterizes the geometric closure and propagation of prediction errors without assuming access to future model outputs. Experiments cover image, video, motion, and audio generation, together with adapted 3D backends. At approximately $5\times$ acceleration, GeoShrink improves FLUX PSNR by 3.10 dB over the strongest listed baseline. On HunyuanVideo, it achieves a reported $4.99\times$ speedup and improves ChronoMagic-Bench-150 PSNR by 5.44 dB over the strongest listed fidelity baseline. Comparisons at fixed evaluation budgets further show substantial gains on motion, audio, music, and 3D generation.
Original source
This story was published by arXiv cs.CV and written by Haosen Li, Wenshuo Chen, Shaofeng Liang, Lei Wang, Bowen Tian, Yutao Yue. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


