Jiafei Duan (@DJiafei)

2026-02-05 | โค๏ธ 129 | ๐Ÿ” 21 | ๐Ÿ’ฌ 2


Why do generalist robotic models fail when a cup is moved just two inches to the left? Itโ€™s not a lack of motor skill, itโ€™s an alignment problem. Today, we introduce VLS: Vision-Language Steering of Pretrained Robot Policies, a training-free framework that guides robot behavior in real time.

Check out the project: https://vision-language-steering.github.io/webpage/ ๐Ÿ‘‡๐Ÿงต (Watch till the end: VLS runs uncut, steering pretrained policies across long-horizon tasks.)


๐Ÿ“„ ์›๋ฌธ ๋‚ด์šฉ

VLS: Steering Pretrained Robot Policies via Visionโ€“Language Models

VLS: Steering Pretrained Robot Policies via Vision-Language Models - A training-free framework for inference-time adaptation of frozen generative robot policies.


๋ฏธ๋””์–ด

๐ŸŽฌ ์˜์ƒ


Tags

AI-ML Robotics