arXiv (All)
open access
Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- DEdit: Iterative Draft Editing for Speculative Decoding#1143111
- Affix Cache for Diffusion Large Language Models#1117561
- The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching#1144310
- OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference#422263
- SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching#1048577
Record · ID 999980
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive