SOURCE-LINKED INTELLIGENCE

Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Diffusion language models decode tokens in parallel, but their bidirectional denoiser rules out the naive key--value (KV) cache behind fast autoregressive inference. Block diffusion restores caching by decoding block-by-block, and the block caches deployed on it so far are tied to attention: O(L)in memory and, if used as training-free retrofits, only an approximation of the model's computation. Both constraints can be overcome: sequence mixers that summarize finalized blocks into a reusable state support block caching, and the corresponding block-causal training objective makes the cache exact

Read original source ↗ Open in workspace

recordType

paper

region

Global