arXiv AI August 18, 2026 By Zirui Song, Yuye Zhu, Yang Yang

Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps

arXiv:2608. 16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different index organizations and dynamic pruning mechanisms.

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

arXiv AI

Aug 3

OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation

arXiv:2603. 17205v3 Announce Type: replace-cross Abstract: Domain-specific finetuning is essential for dense retrievers, yet not all data pairs contribute equally to the learning process.

By Haoyang Fang, Shuai Zhang, Yifei Ma, Hengyi Wang, Cuixiong Hu, Katrin Kirchhoff, Bernie Wang, George Karypis

llms rag fine-tuning efficiency

arXiv Machine Learning

Jun 9

Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy

arXiv:2606. 09080v1 Announce Type: new Abstract: Pruning has emerged as a dominant paradigm for accelerating large language model (LLM) inference, spanning a broad spectrum of methods that remove computation across tokens, layers, heads, dimensions, and attention patterns.

By Haozhe Hu, Hao Wu, Anhao Zhao, Longwei Ding, Peiran Yin, Yunpu Ma, Xiaoyu Shen

llms nlp efficiency benchmarks

arXiv Machine Learning

Jul 20

VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs

arXiv:2607. 15498v1 Announce Type: cross Abstract: The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference.

By Shahrzad Esmat, Dhawal Shah, Ali Jannesari

llms efficiency benchmarks

arXiv Machine Learning

Jul 31

Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention

arXiv:2607. 27692v1 Announce Type: cross Abstract: Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries.

By Wenshuai Yao, Wenyong Zhou, Hanyong Shao, Yizhe Chen, Zhiyuan Ning, Yuannuo Feng, Ru Huang, Kechao Tang

efficiency

arXiv AI

Jun 16

SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases

arXiv:2511. 16681v3 Announce Type: replace-cross Abstract: Vector databases (VecDBs) are increasingly deployed in retrieval-augmented generation (RAG) pipelines where query processing and document ingestion occur concurrently.

By Dong Liu, Yanxuan Yu

rag efficiency

arXiv Machine Learning

Aug 5

ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference

arXiv:2608. 02947v1 Announce Type: new Abstract: The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can discriminate position.

By Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri

llms rag efficiency benchmarks

Related stories

OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation

Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy

VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs

Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention

SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases

ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference