# mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations

arXiv: https://arxiv.org/abs/2510.02348 · HTML: https://mlsanity.com/paper/2510.02348/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [NIPS 2016 Tutorial: Generative Adversarial Networks](https://mlsanity.com/paper/1701.00160/) (2016)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Information Leakage in Embedding Models](https://mlsanity.com/paper/2004.00053/) (2020)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [Relative representations enable zero-shot latent space communication](https://mlsanity.com/paper/2209.15430/) (2022)
- [Unsupervised Neural Machine Translation](https://mlsanity.com/paper/1710.11041/) (2017)
- [A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings](https://mlsanity.com/paper/1805.06297/) (2018)
- [Analyzing Transformers in Embedding Space](https://mlsanity.com/paper/2209.02535/) (2022)
- [Gromov-Wasserstein Alignment of Word Embedding Spaces](https://mlsanity.com/paper/1809.00013/) (2018)
- [Jasper and Stella: distillation of SOTA embedding models](https://mlsanity.com/paper/2412.19048/) (2024)
- [Unsupervised Alignment of Embeddings with Wasserstein Procrustes](https://mlsanity.com/paper/1805.11222/) (2018)
- [Harnessing the Universal Geometry of Embeddings](https://mlsanity.com/paper/2505.12540/) (2025)
- [Do Vision and Language Encoders Represent the World Similarly?](https://mlsanity.com/paper/2401.05224/) (2024)
- [Non-Adversarial Unsupervised Word Translation](https://mlsanity.com/paper/1801.06126/) (2018)
- [Discovering Universal Geometry in Embeddings with ICA](https://mlsanity.com/paper/2305.13175/) (2023)
- [Unsupervised Multilingual Word Embeddings](https://mlsanity.com/paper/1808.08933/) (2018)
- [It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data](https://mlsanity.com/paper/2503.24129/) (2025)

## Built on by (most cited first, 4 of 4)

- [Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale](https://mlsanity.com/paper/2604.18572/) (2026)
- [Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry](https://mlsanity.com/paper/2605.20496/) (2026)
- [Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data](https://mlsanity.com/paper/2610.09411/) (2026)
- [Unpaired Canonical Correlation Analysis](https://mlsanity.com/paper/2610.09530/) (2026)

## Abstract (arXiv)

We build upon vec2vec, a procedure designed to align text embedding spaces without parallel data. vec2vec finds a near-perfect alignment, but it is expensive and unstable. We present mini-vec2vec, a simple and efficient alternative that requires substantially lower computational cost and is highly robust. Moreover, the learned mapping is a linear transformation. Our method consists of three main stages: a tentative matching of pseudo-parallel embedding vectors, transformation fitting, and iterative refinement. Our linear alternative exceeds the original instantiation of vec2vec by orders of magnitude in efficiency, while matching or exceeding their results. The method's stability and interpretable algorithmic steps facilitate scaling and unlock new opportunities for adoption in new domains and fields.