---
title: "Latent-Lens: Visual Perception in Small Language Models Through Latent Communication"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.41751v1"
permalink: "https://feed.astralor.com/items/itm_eacbb23dcf50da89e92aee94"
published: "2026-10-30T13:53:44.000Z"
score: 57
channel: "ai"
tags: ["AI Agent","多模态","Latent-Lens","Visual Perception","Small Language Models","Through Latent Communication","Bridging","VLMs"]
---

# Latent-Lens: Visual Perception in Small Language Models Through Latent Communication

## At a glance

Bridging independent vision-language models (VLMs) and small language models (SLMs) in a modular multi-agent system typically forces them to exchange information as discrete text, which creates a lossy bottleneck for sp…

## Key points

- Bridging independent vision-language models (VLMs) and small language models (SLMs) in a modular multi-agent system typically forces them to exchange information as discrete text, which creates a lossy bottleneck for sp…
- This constraint is especially acute for SLMs, whose limited capacity makes them more reliant on the quality of the input signal.
- Recent latent-communication methods exchange states between language models.

## Full text

Bridging independent vision-language models (VLMs) and small language models (SLMs) in a modular multi-agent system typically forces them to exchange information as discrete text, which creates a lossy bottleneck for spatial and fine-grained details. This constraint is especially acute for SLMs, whose limited capacity makes them more reliant on the quality of the input signal. Recent latent-communication methods exchange states between language models. How a VLM can pass visual information to a separately pretrained text-only SLM though remains unexplored. We propose \textbf{Latent-Lens}, a lightweight codec that bridges the representation gap between a frozen VLM and a frozen SLM directly in latent space, enabling them to communicate purely through hidden states. The codec consists of a domain encoder that projects hidden states from the VLM into the SLM's embedding space, and an attention decoder formalised as a LoRA that teaches the SLM to attend to these visual prefixes, while training only ${\sim}1.6$M parameters (0.2\% of the combined model size). On visual question answering (CLEVR, GQA), Latent-Lens achieves $81.0\pm7.9$\% and $65.4\pm5.4$\%, compared with $58.3\pm5.7$\% and $61.8\pm1.0$\% for text communication with the same LoRA budget (+30.2--69.8pp relative to frozen text communication), while on image captioning (Flickr8k) it improves over the same baseline by +16.5 (+18.8 frozen). We also evaluate Latent-Lens with TinyLlama-1.1B and InternVL2-1B, which use different architectures, vocabularies, and hidden dimensions.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_eacbb23dcf50da89e92aee94