---
license: mit
library_name: transformers
pipeline_tag: image-text-to-text
---

# ReToken: One Token to Improve Vision–Language Models for Visual Retrieval

This repository contains the model from the paper [ReToken: One Token to Improve Vision-Language Models for Visual Retrieval](https://huggingface.co/papers/2607.28627).

**ReToken** is a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache.

Code: https://github.com/avaxiao/ReToken