paper-with-me

Papers

Harnessing the Universal Geometry of Embeddings

2025-05-18 · Rishi Jha, Collin Zhang, Vitaly Shmatikov, John X. Morris

We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches. Our unsupervised approach translates any embedding to and from a universal latent representation (i.e., a universal semantic structure conjectured by the Platonic Representation Hypothesis). Our translations achieve high cosine similarity across model pairs with different architectures, parameter counts, and training datasets. The ability to translate unknown embeddings into a different space while preserving their geometry has serious implications for the security of vector databases. An adversary with access only to embedding vectors can extract sensitive information about the underlying documents, sufficient for classification and attribute inference.

📄 PDF Abstract BibTeX arXiv:2505.12540

Code (2)

rjha18/vec2vec 공식 구현 pytorch
zhaoolee/garss pytorch

Tasks

Attribute

Similar Papers 제목 키워드 기반

Discovering Universal Geometry in Embeddings with ICA

2023-05-22 · Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira

This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images. Our approach extracts independent semantic components from the embeddings of a pre-…

Harnessing Data Asymmetry: Manifold Learning in the Finsler World

2026-03-12 · Thomas Dagès, Simon Weber, Daniel Cremers, Ron Kimmel arxiv

Manifold learning is a fundamental task at the core of data analysis and visualisation. It aims to capture the simple underlying structure of complex high-dimensional data by preserving pairwise dissimilarities in low-di…

Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry

2026-05-19 · Pablo Marcos-Manchón, Rishi Jha, Lluís Fuentemilla arxiv

The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively: embeddings can be translated across models through a universal laten…

Simplicial Representation Learning with Neural $k$-Forms

2023-12-13 · Kelly Maggs, Celia Hacker, Bastian Rieck

Geometric deep learning extends deep learning to incorporate information about the geometry and topology data, especially in complex domains like graphs. Despite the popularity of message passing in this field, it has li…

Deep LearningRepresentation Learning

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval

2025-06-17 · Ruofan Hu, Yan Xia, Minjie Hong, Jieming Zhu 외

Multimodal large language models (MLLMs) have seen substantial progress in recent years. However, their ability to represent multimodal information in the acoustic domain remains underexplored. In this work, we introduce…

In-Context LearningRetrieval