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.
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...
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.
arXiv:2607. 03515v1 Announce Type: cross Abstract: In many machine learning applications, the most relevant items for a query should be efficiently retrieved.
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...
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.
arXiv:2506. 22271v3 Announce Type: replace Abstract: Neural networks often map low-dimensional embeddings to high-dimensional output spaces.
CORE improves compositional reasoning in multimodal language models by distilling a cross‑attentive reranker’s fine‑grained judgments into the embedding model. It generates candidate lists across five compositional matching levels and trains with a Rank‑KL objective to replicate the reranker’s ranking. Experiments on COLA, SUGARCREPE++, and NEGBENCH show CORE‑RERANKER‑8B outperforms Jina‑Reranker by 10.7 points, while CORE‑EMBED‑8B achieves the best overall average among evaluated embeddings, with gains also transferring to the MCMR benchmark without harming COCO or Flickr30K retrieval.
arXiv:2605. 20689v2 Announce Type: replace-cross Abstract: High-dimensional language-model embeddings increase storage and search costs, while supervised compressors can overfit when relevance labels are scarce.
arXiv:2505. 17810v2 Announce Type: replace Abstract: Approximate nearest neighbor (ANN) search is a performance-critical component of many machine learning pipelines, and rigorous benchmarking is essential for assessing the performance of vector indexes for ANN search.
The paper introduces a compositional graph embedding framework based on Aitchison geometry, where nodes are represented as simplex-valued mixtures over latent archetypal factors. By embedding these mixtures using isometric log-ratio coordinates, the method preserves Aitchison distances while allowing unconstrained optimization in Euclidean space, yielding intrinsically interpretable embeddings. The approach achieves competitive performance on node classification and link prediction tasks and enables principled component restriction through subcompositional coherence, allowing analysis of how archetype groups influence representations and predictions.
arXiv:2607. 18027v1 Announce Type: new Abstract: Scaled dot product attention conflates directional alignment and vector magnitude, limiting its effectiveness as a similarity metric in Transformer models.
The paper investigates how dimensionality reduction and quantization together affect text embedding compression across four task families in the Massive Text Embedding Benchmark using five pretrained models. It finds that combining these techniques can preserve near-original performance while drastically reducing storage, with some classification models retaining at least 99% of their score using less than 0.1% of the original storage. The optimal trade‑off between dimensionality and bit‑width varies by task, with retrieval tasks being more sensitive to compression.