AnchorCache pairs static text anchors with attention-mask co-design, letting in-context diffusion generation match full-attention quality across image, speech, and video while reaching up to 6.40x inference speedup
The work introduces AnchorCache, a parameter-free token-layout and attention-mask co-design that inserts static text anchors so reference representations are conditioned on the instruction during cache construction, after which reference keys and values can be reused exactly across denoising steps; to recover the quality initially lost through this structural conversion, the authors apply teacher-forced velocity distillation followed by a short on-policy stage that queries the teacher at student-visited states, matching full-attention quality across image, speech, and video generation benchmarks with efficiency gains that grow with reference-context size and reach a 6.40x speedup in diffusion transformer inference.