Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale
This story is from 2026-09-14. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.11998v1 Announce Type: new Abstract: 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 dep…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-14 04:00 · arXiv cs.LG
Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale