Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

ReToken: A Single Learnable Token Boosts Vision-Language Models for Visual Retrieval

AI By Crimson AI Hugging Face Papers 1 August 2026 · 00:00 19 views
Share: X Telegram

ReToken introduces a single learnable embedding that acts as an explicit retrieval target, selecting sparse query-relevant visual tokens from a pre-filled KV cache. It improves performance on image and video benchmarks while fitting training and long-video inference on a single H100 GPU.

ReToken: A Single Learnable Token Boosts Vision-Language Models for Visual Retrieval

Key points

Long visual contexts remain a significant hurdle for vision-language models (VLMs), as performance degrades with an increasing number of distractors and processing all tokens simultaneously becomes computationally prohibitive under GPU memory limits. A new paper introduces ReToken, a method that tackles this challenge with a single learnable embedding designed as an explicit retrieval target.

ReToken operates by selecting a sparse set of query-relevant visual tokens from a pre-filled visual KV cache. This approach avoids the need to process the entire visual context at once, making it both efficient and effective. The method is trained on only a small image-QA dataset, yet it delivers consistent gains across multiple benchmarks.

On the Visual Haystacks benchmark, ReToken improves Qwen3VL-8B by 13.4 points and InternVL3.5 by 12.4 points, representing over 20% relative improvement. For video, the method transfers zero-shot to long-video tasks on LVBench, yielding an 8.0-point gain with Qwen3VL-8B.

Thanks to its lightweight design, both training and long-video inference can be performed on a single H100 GPU. The code is publicly available on GitHub, enabling further research and adoption.

BenchmarkModelImprovement (points)
Visual HaystacksQwen3VL-8B13.4
Visual HaystacksInternVL3.512.4
LVBenchQwen3VL-8B8.0
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1