2 papers
cs.RO2026
DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation
Haoran Yuan, Zekai Wang, Boning Shao +4
Dexterous manipulation depends on contact dynamics that are often only partially observable from vision. Recent World-Action Models (WAMs) couple predictive video world modeling wi…
cs.RO2026
VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs
Haoran Yuan, Weigang Yi, Zhenyu Zhang +9
Video-Action Models (VAMs) have emerged as a promising framework for embodied intelligence, learning implicit world dynamics from raw video streams to produce temporally consistent…