SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.18489 · 2026

EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models

Woosang Lim, Sungjoo Yoo, Donghyun Son, Minsoo Cheong

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by selectively updating cached states, but their decision overhead scales with context length or model depth. We propose ENTROPYCACHE, a training-free KV caching method that uses the maximum entropy of newly decoded token distributions as a constant-cost signal for deciding when to recompute. Our design is grounded in two empirical observations: (1) decoded token entropy correlates with KV cache drift, providing a cheap proxy for cache staleness, and (2) feature volatility of decoded tokens persists for multiple steps after unmasking, motivating recomputation of the k most recently decoded tokens. The skip-or-recompute decision requires only O(V ) computation per step, independent of context length and model scale. Experiments on LLaDA-8B-Instruct and Dream-7B-Instruct show that ENTROPYCACHE achieves 15.2×-26.4× speedup on standard benchmarks and 22.4×-24.1× on chain-of-thought benchmarks, with competitive accuracy and decision overhead accounting for only 0.5% of inference time. Code is available at https://github.com/mscheong01/EntropyCache

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.18489")
get_code_for_paper("2603.18489")
have("2603.18489")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2603.18489.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2603.18489.svg)](https://syntology.ai/paper/2603.18489)

Connect an agent — have() is free.