Showing 2026Show all
2 papers · 1 filter
cs.RO2026
EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
Ruixiang Wang, Qingming Liu, Yueci Deng +3
Video generative models offer a promising basis for robotic planning by predicting future visual rollouts from observations and task instructions. However, their training objective…
cs.CV2026
PAct: Part-Decomposed Single-View Articulated Object Generation
Qingming Liu, Xinyue Yao, Shuyuan Zhang +4
Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR, where functional part decomposition and kinematic motion are essential.…