---
title: "RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control"
description: "RT-2 turns low-level robot actions into the same kind of tokens a vision-language model already writes. Follow the shared vocabulary, co-fine-tuning recipe, transfer evidence, cloud control loop, and the boundary between new semantic uses and new physical skills."
canonical_url: "https://fanout.sh/daily/2026-11-10-rt2-vision-language-action"
md_url: "https://fanout.sh/daily/2026-11-10-rt2-vision-language-action.md"
last_updated: "2026-11-10"
access: "public"
---

# RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

RT-2 turns low-level robot actions into the same kind of tokens a vision-language model already writes. Follow the shared vocabulary, co-fine-tuning recipe, transfer evidence, cloud control loop, and the boundary between new semantic uses and new physical skills.

## Paper details

- Authors: Anthony Brohan et al.

- Venue: CoRL 2023

- Track: AI Research

- Difficulty: Medium

- Reading time: 10 min

- Original paper: https://arxiv.org/abs/2307.15818v1

## What you will learn

- How eight discretized action values let one vision-language model share every weight across web and robot tasks.

- Why mixing the original web tasks into robot fine-tuning matters more than simply attaching a larger pretrained model.

- What the seen, unseen, and emergent-skill evaluations establish, and why scale, latency, and narrow robot motions bound the result.

## Continue exploring

[Compare a compact modern VLA](https://fanout.sh/daily/2026-10-06-smolvla-affordable-robotics): Contrast RT-2's large cloud-served token policy with SmolVLA's compact action-chunking design and asynchronous execution loop.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md
