method · first seen 16 Nov 2026
vision-language-action control
Using pretrained multimodal models to output robot control actions directly from images and language.
Mentions per week
PapersCodeDiscussion
Earliest sources
- ForceHarness: Turning Force into Action and Physics for Frozen Frontier ModelsPapers · 16 Nov 2026 · Ke Sun, Kevin Yuchen Ma, Yike Zhang, Yanzhe Chen, Mike Zheng Shou
Latest sources
- ForceHarness: Turning Force into Action and Physics for Frozen Frontier ModelsPapers · 16 Nov 2026 · Ke Sun, Kevin Yuchen Ma, Yike Zhang, Yanzhe Chen, Mike Zheng Shou