arXiv Computation and Language October 16, 2026 By Xuning He, Qingyuan Shi, Zinan Sheng, Yongding Tao, Huanyu Liu, Ge Li, Xue Jiang, Yihong Dong

Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models

Read the original on arXiv Computation and Language →

The paper introduces Archer, a training‑free caching method that enables efficient rollback in diffusion language models by reusing cached hidden states within a bounded neighborhood. Archer recomputes mutable responses at each update while reusing prompt key/value pairs, thereby amortizing prompt computation without limiting rollback capability. Experiments on code‑generation and non‑code benchmarks show significant speedups—up to 4.33× over LLaDA‑Confidence—while maintaining or improving accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jun 3

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.

By Zhiyuan Liu, Yicun Yang, Yaojie Zhang, Junjie Chen, Chang Zou, Qingyuan Wei, Shaobo Wang, Yichen Zhu, Linfeng Zhang

llms diffusion efficiency

arXiv AI

Oct 12

ReplaySSM: Cache SSM Inputs, Not State

ReplaySSM is a technique that redefines how state-space models (SSMs) handle their recurrent state by caching SSM inputs instead of the state itself. It unrolls the recurrence into a checkpoint plus a buffer of recent inputs, reducing state memory traffic by about half and enabling efficient speculative rollback. The method also allows separate precision levels for checkpoints, improving output accuracy while accelerating decoding in hybrid models such as Mamba-2 and Gated DeltaNet.

By Ze-Wei Liou, Harris Nover, Amey Naik, Andrii Skliar, Igor Shovkun, Ido Shahaf, Tri Dao

efficiency

arXiv Machine Learning

Jul 31

Back from the Future: Key-Value Cache Management by Counter-Causal Surprise

arXiv:2607. 27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.

By Stephen Gould, Anton van den Hengel

llms efficiency multimodal benchmarks

Hugging Face Trending Papers

Jul 5

Sangam: Efficiently Serving Diffusion LLMs with the AR Stack

Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation. Their bidirectional attention prevents exact autoregressive-style KV caching, since committing one position shifts the KV activations of all others.

llms diffusion

arXiv Machine Learning

Sep 29

CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters

CacheReforge is a method for recovering stale key‑value (KV) caches in large language models when lightweight adapters evolve. It represents stale caches as layer‑wise mixed‑version objects and uses adapter anchors, sensitivity calibration, drift accumulation, and restart boundaries to decide between direct reuse, bounded recomputation, or full suffix recovery. Experiments on Qwen2.5 models with continual LoRA updates show a 92.4% reduction in mean KL divergence while only recomputing 5.44% of layers and cutting cache‑maintenance time by 93.2% compared to full prefill.

By Yuhang Cao, Yanzhou Mu, Chunrong Fang, Zhenyu Chen

llms fine-tuning

arXiv Computation and Language

Sep 23

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.

By Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen

llms diffusion efficiency benchmarks