arXiv Machine Learning June 30, 2026 By Tianyu Wang, Gourav Rattihalli, Aditya Dhakal, Junbo Li, Zhiwei Ren, Dejan Milojicic, Longfei Shangguan

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

Read the original on arXiv Machine Learning →

arXiv:2606. 30389v1 Announce Type: new Abstract: Dynamic sparse attention (DSA) accelerates long-context LLM decoding by attending to only the top-K KV blocks relevant to each query, but it introduces a serialized selection-to-attention dependency that emerges as a new latency bottleneck.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 24

The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs

arXiv:2504. 17768v3 Announce Type: replace-cross Abstract: Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency-accuracy trade-offs remain unclear due to the lack of comprehensive evaluation.

By Piotr Nawrot, Robert Li, Renjie Huang, Sebastian Ruder, Kelly Marchisio, Edoardo M. Ponti

llms efficiency

arXiv Machine Learning

Jun 25

Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding

arXiv:2606. 24957v1 Announce Type: cross Abstract: While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck where Key-Value (KV) cache loading dominates latency.

By WenHung Lee, Jian-Jia Chen, Xiaolin Lin, Pei-Shuo Wang, Chi-Chih Chang, Chun-Che Yang, Ning-Chi Huang, Grace Li Zhang, Kai-Chiang Wu

llms efficiency

arXiv Machine Learning

Jul 2

FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel

arXiv:2508. 18224v3 Announce Type: replace-cross Abstract: Recent advances in sparse attention mechanisms have demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs).

By Ran Yan, Youhe Jiang, Zhuoming Chen, Haohui Mai, Beidi Chen, Binhang Yuan

llms benchmarks

arXiv Machine Learning

Jun 29

Simplified Sparse Attention via Gist Tokens

arXiv:2604. 20920v2 Announce Type: replace Abstract: Sparse attention can reduce the cost of long-context inference, but most variants introduce new architectural components.

By Yuzhen Mao, Michael Y. Li, Emily B. Fox

llms rag efficiency

arXiv Machine Learning

Jun 2

Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention

arXiv:2602. 07223v2 Announce Type: replace Abstract: Long-context large language model (LLM) inference has become the norm for today's AI applications.

By Yikang Yue, Yuqi Xue, Jian Huang

llms efficiency benchmarks

arXiv AI

Jul 2

Stateful Token Reduction for Long-Video Hybrid VLMs

arXiv:2603. 00198v2 Announce Type: replace-cross Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning.

By Jindong Jiang, Amala Sanjay Deshmukh, Kateryna Chumachenko, Karan Sapra, Zhiding Yu, Guilin Liu, Andrew Tao, Pavlo Molchanov, Jan Kautz, Wonmin Byeon

llms fine-tuning efficiency benchmarks

Related stories

The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs

Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding

FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel

Simplified Sparse Attention via Gist Tokens

Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention

Stateful Token Reduction for Long-Video Hybrid VLMs