README.md

---
title: README
emoji: 🌐
colorFrom: blue
colorTo: gray
sdk: static
pinned: false
---

<div align="center">
  <img src="logo.svg" width="150" alt="hyper³labs logo" />
  <h1>hyper³labs</h1>
  <p><strong>Embedding models and retrieval infrastructure.</strong></p>
  <p>
    <a href="https://hyper3labs.com">Website</a> ·
    <a href="https://github.com/Hyper3Labs">GitHub</a>
  </p>
</div>

hyper³labs (pronounced *Hypercube Labs*) builds embedding models and retrieval infrastructure across text and vision. We also build open-source tools for evaluating and understanding embedding systems.

We are especially interested in how hierarchy and non-Euclidean geometry affect retrieval, and in the failures that aggregate benchmark scores hide.

## Models

- **[hyper3-clip-v0.5](https://huggingface.co/hyper3labs/hyper3-clip-v0.5)** is an open-weight vision-language embedding model for hierarchy-sensitive retrieval. It produces 512-dimensional embeddings and works with the Sentence Transformers interface.

## Tools and demos

- **[HyperView](https://huggingface.co/spaces/hyper3labs/HyperView)** is our open-source workbench for exploring embedding spaces and tracing retrieval failures back to real samples.
- **[ABO Catalog Explorer](https://huggingface.co/spaces/hyper3labs/HyperView-ABO-Catalog)** tests fine-grained retrieval on product catalogs.
- **[DeepFashion Search](https://huggingface.co/spaces/hyper3labs/HyperView-DeepFashion-Text-Search)** explores text-to-image search for garments and product attributes.
- **[Precision Region Search](https://huggingface.co/spaces/hyper3labs/precision-region-search-refcocog-hyper3clip)** demonstrates referring-expression retrieval on RefCOCOg.
- **[Jaguar Re-ID](https://huggingface.co/spaces/hyper3labs/HyperView-Jaguar-ReID)** examines whether re-identification models recognize an animal or its background.
- **[VisA Industrial Search](https://huggingface.co/spaces/hyper3labs/HyperView-VisA-Manufacturing)** explores anomaly and part retrieval in industrial imagery.

## Datasets

- **[jaguar-re-id](https://huggingface.co/datasets/hyper3labs/jaguar-re-id)**: individual jaguar identification from spot patterns.
- **[amazon-berkeley-objects](https://huggingface.co/datasets/hyper3labs/amazon-berkeley-objects)**: a mirror used for hierarchical product retrieval evaluation.
- **[jaguar-hyperview-demo](https://huggingface.co/datasets/hyper3labs/jaguar-hyperview-demo)**: a smaller subset prepared for interactive analysis.

## Research

**[Are We Recognizing the Jaguar or Its Background? A Diagnostic Framework for Jaguar Re-Identification](https://arxiv.org/abs/2604.09690)**  
Antonio Rueda-Toicen, Robert Vava, Matin Mahmood. April 2026.