PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
Published in Robotics: Science and Systems (RSS) 2026, 2026
Authors: Shizhe Chen, Paul Pacaud, and Cordelia Schmid https://arxiv.org/abs/2605.21414
TLDR; PointACT introduces a vision-language-action model with multi-scale point-action interaction for robotic manipulation.
S. Chen, P. Pacaud and C. Schmid, “PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction,” Robotics: Science and Systems (RSS), 2026.