arXiv Machine Learning June 5, 2026 By Tomonaga Okabe, Kazuhiko Komatsu

Knowledge Manifold: A Riemannian Geometric Framework for Semantic Mapping and Geodesic Analysis of Scientific Literature

Read the original on arXiv Machine Learning →

arXiv:2606. 05907v1 Announce Type: cross Abstract: We present the knowledge manifold: a Riemannian geometric space in which a corpus of documents is arranged according to semantic positional relationships derived from character n-gram TF-IDF representations.

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

arXiv Machine Learning

Jun 5

Geodesic Semantic Search: Cartographic Navigation of Citation Graphs with Learned Local Riemannian Maps

arXiv:2602. 23665v5 Announce Type: replace-cross Abstract: We present Geodesic Semantic Search (GSS), a retrieval system that learns node-specific Riemannian metrics on citation graphs to enable geometry-aware semantic search.

By Brandon Yee, Lucas Wang, Kundana Kommini

rag benchmarks

arXiv Machine Learning

1d ago

Iso-Riemannian Optimization on Learned Data Manifolds

arXiv:2510. 21033v3 Announce Type: replace-cross Abstract: We develop a theory of iso-Riemannian optimization for problems constrained to learned data manifolds, a setting in which classical Riemannian optimization - and Riemannian gradient descent in particular - can be poorly suited.

By Willem Diepeveen, Melanie Weber

arXiv AI

Jun 3

Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation

arXiv:2606. 03307v1 Announce Type: cross Abstract: Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain inference.

By Yifan Jin, Qirui Ji, Bin Qin, Jiangmeng Li, Lixiang Liu, Fuchun Sun, Changwen Zheng

rag benchmarks

arXiv Machine Learning

Aug 4

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding

arXiv:2605. 13352v2 Announce Type: replace Abstract: Standard dual-encoder vision-language models that map images and text to deterministic points on a shared unit hypersphere through $\ell_2$ normalization typically expose neither \emph{aleatoric} uncertainty (cross-modal ambiguity) nor \emph{epistemic} uncertainty (lack of training-distribution support).

By Mayank Nautiyal, Li Ju, Andreas Hellander, Ekta Vats, Prashant Singh

llms rag diffusion multimodal benchmarks

arXiv Machine Learning

Jul 16

The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model

arXiv:2607. 13660v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyperspherical geometry.

By Zijie Yu, Gaowen Liu, Ramana Rao Kompella, Philip S. Yu, Yue Song

rag diffusion multimodal

arXiv AI

Jul 9

Riemannian Geometry for Pre-trained Language Model Embeddings

arXiv:2607. 07047v1 Announce Type: cross Abstract: Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety.

By Szczepan Konior, Alexandre Quemy, Przemys{\l}aw Klocek, Gr\'egoire Cattan, Bart{\l}omiej Sobieski

llms rag benchmarks safety

Related stories

Geodesic Semantic Search: Cartographic Navigation of Citation Graphs with Learned Local Riemannian Maps

Iso-Riemannian Optimization on Learned Data Manifolds

Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding

The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model

Riemannian Geometry for Pre-trained Language Model Embeddings