arXiv AI June 9, 2026 By Sean Moran

Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era

arXiv:2510. 04127v2 Announce Type: replace-cross Abstract: Approximate nearest neighbour (ANN) search underpins large-scale retrieval, increasingly within the retrieval-augmented generation pipelines that ground large language models, yet the methods that address it have multiplied across communities until they are seldom read as a single field.

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

arXiv Machine Learning

1d ago

NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction

arXiv:2608. 15438v1 Announce Type: cross Abstract: Building approximate nearest neighbor (ANN) indexes at billion scale is often dominated by expensive global clustering or graph construction, making time-to-index a first-order systems concern.

By Xingqiao Wang, Zi Wang, Xiaowei Xu

rag efficiency benchmarks

arXiv AI

Jun 30

Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval

arXiv:2606. 30473v1 Announce Type: cross Abstract: We study retrieval over catalogs of structured metadata, where each record is a small schema whose fields answer different kinds of query.

By Aivin V. Solatorio, Olivier Dupriez, Rafael Macalaba

llms rag agents fine-tuning benchmarks

arXiv Machine Learning

Jul 9

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference

arXiv:2607. 07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantization, eviction, or offloading.

By Vladimir Gusev

llms efficiency

arXiv AI

Aug 6

Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms

arXiv:2608. 04074v1 Announce Type: cross Abstract: Long-context LLM decoding reads the key-value (KV) cache at every step.

By Samuel Fern\'andez-Mendui\~na, Amir Ziashahabi, Eduardo Pavez, Antonio Ortega, Salman Avestimehr

llms efficiency

Hugging Face Trending Papers

Jul 27

DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing

Semantic hashing methods for generating short binary hash codes that allow efficient approximate nearest neighbor search in high-dimensional data spaces have gained extensive consideration in recent years. Deep learning-based methods offer better semantic capturing capabilities than traditional approaches relying on manual feature engineering.

multimodal benchmarks

arXiv AI

Jun 18

RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation

arXiv:2606. 18379v1 Announce Type: cross Abstract: Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation learning, and real-time serving -- yet existing work addresses each in isolation.

By Renzhi Wu, Zikun Cui, Junjie Yang, Tai Guo, Hong Li, Xian Chen, Li Yu, Ke Pan, Sri Reddy, Mahesh Srinivasan, Nipun Mathur, Haomin Yu, Hong Yan

efficiency safety

Related stories

NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction

Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference

Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms

DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing

RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation