arXiv Computer Vision October 22, 2026 By Nikita Gabdullin, Anton Raskovalov

Latent space configuration for neural network finetuning, fast ranking, and embedding dimensionality reduction

Read the original on arXiv Computer Vision →

The paper introduces Latent Space Configuration (LSC) for fine‑tuning neural networks, enabling the creation of structured latent spaces that accelerate top‑K retrieval with O(1) candidate search. Using ArcFace‑pretrained IResNet50 models, the authors demonstrate up to three‑fold GPU speed‑ups and 40% CPU speed‑ups over exhaustive search, while also showing that reducing latent space dimensionality further speeds up queries and can improve rank‑N metrics.

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 Computer Vision.

arXiv AI

Aug 25

Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval

arXiv:2608.22980v1 Announce Type: cross Abstract: Dense vector retrieval has become the foundation of modern semantic search, yet existing approximate nearest neighbor (ANN) indexes treat an embeddin...

By Kishore Konda

rag

arXiv AI

Jun 3

$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval

arXiv:2601. 20844v3 Announce Type: replace-cross Abstract: This paper studies the Minimal Embeddable Dimension (MED): the least dimension in which there exists a configuration of $m$ object vectors so that every subset of size at most $k$ is exactly retrieved by score comparison.

By Zihao Wang, Hang Yin, Lihui Liu, Hanghang Tong, Yangqiu Song, Ginny Wong, Simon See

llms rag

arXiv Machine Learning

Jul 7

Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls

arXiv:2607. 03515v1 Announce Type: cross Abstract: In many machine learning applications, the most relevant items for a query should be efficiently retrieved.

By Kirill Shevkunov, Andrey Ploskonosov, Liudmila Prokhorenkova

rag

arXiv Machine Learning

Sep 30

DimGrow: Memory-Efficient Field-level Embedding Dimension Search

arXiv:2505.12683v2 Announce Type: replace Abstract: Key feature fields need bigger embedding dimensionality, others need smaller. This demands automated dimension allocation. Existing approaches, suc...

By Yihong Huang, Chen Chu

rag efficiency

arXiv Machine Learning

Oct 5

Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically Easy

The paper investigates the geometric capacity of vector retrieval systems, focusing on the maximum recall achievable with a fixed document index. It demonstrates that, on real-world benchmarks, single-vector query encoders often underperform relative to the index’s potential. The authors provide theoretical evidence that learning such encoders can be computationally hard, constructing a task where a simple neural network can achieve perfect recall while any statistical-query learner would need exponentially many queries to surpass random chance.

By Anders Wikum, Nina Mishra, Amin Saberi, Tal Wagner

rag benchmarks

arXiv AI

Jun 2

On the Theoretical Limitations of Embedding-based Link Prediction

arXiv:2506. 22271v3 Announce Type: replace Abstract: Neural networks often map low-dimensional embeddings to high-dimensional output spaces.

By Samy Badreddine, Emile van Krieken, Luciano Serafini

rag

One email a morning, machine-written

Related stories

Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval

$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval

Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls

DimGrow: Memory-Efficient Field-level Embedding Dimension Search

Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically Easy

On the Theoretical Limitations of Embedding-based Link Prediction