Vision language models control robots through simple action interfaces
Show-Harness: Just a VLM Agent Can Play Robots
RoboticsArtificial IntelligenceComputer Vision and Pattern RecognitionMultimedia
Summary
Controlling robots using advanced vision and language AI is hard because these models need to connect their understanding to physical actions. The authors created Show-Harness, a tool that links a vision-language model's intentions to specific robot moves using clear and simple commands. This lets both powerful closed-source models and smaller open-source ones control robots without needing extra complex training. They also made a related system, GUMI, that helps humans and AI teach robots by interacting with graphical interfaces, so special equipment isn't needed. Their tests show that this approach works well across different robots and tasks, making AI-based robot control more practical.
vision-language modelsrobot controlsemantic interfacezero-shot learningfine-tuningembodimentGUI manipulationteleoperationfoundation modelszero-shot robot control
Authors
Yanzhe Chen, Zechen Bai, Zhijun Cao, Wenzheng Zeng, Kevin Qinghong Lin, Yiqi Lin, Guoqiang Liang, Kevin Yuchen Ma, Qiming Huang, Mike Zheng Shou
Abstract
Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play" robots through a compact semantic interface linking intent to action. Show-Harness exposes discrete semantic action units that VLMs can naturally reason over, while embodiment-specific interpreters deterministically ground them into local robot actions, keeping the VLM directly responsible for fine-grained physical decisions. Through the same interface, Show-Harness demonstrates the feasibility of (1) directly unlocking closed-source frontier VLMs for zero-shot robot control, and (2) adapting small-scale open-source VLMs for low-cost deployment with just a few GPU-hours of fine-tuning. We further develop GUMI (GUI Manipulation Interface), which extends the same semantic action space to GUI-based demonstration collection, allowing humans and agents to "play" robots across embodiments without specialized teleoperation hardware. Extensive experiments show that Show-Harness-equipped VLM agents generalize robustly across tasks, embodiments, and environments, outperforming representative agentic and VLA paradigms. These results suggest that the right interface can unlock substantial embodied capability from foundation VLMs, without requiring additional model capacity or costly embodiment-specific pretraining.