6 papers
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Kevin Qu, Tao Sun, Massimiliano Viola +5
Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer…
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models
Lin Sun, Zhiwei Guan, Conglin Wang +7
Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for efficiency, yet they face a fu…
Energy-based Compositional Diffusion Planning
Tao Sun, Utkarsh Aashu Mishra, Jiaxin Lu +2
Compositional diffusion planners aim to solve long-horizon robotic tasks using short training trajectories. Yet, current approaches often rely on the heuristic stitching of local p…
Do 3D Large Language Models Really Understand 3D Spatial Relationships?
Xianzheng Ma, Tao Sun, Shuai Chen +7
Recent 3D Large-Language Models (3D-LLMs) claim to understand 3D worlds, especially spatial relationships among objects. Yet, we find that simply fine-tuning a language model on te…
Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
Yue Pan, Tao Sun, Liyuan Zhu +4
Point cloud registration aligns multiple unposed point clouds into a common reference frame and is a core step for 3D reconstruction and robot localization without initial guess. I…
Rectified Point Flow: Generic Point Cloud Pose Estimation
Tao Sun, Liyuan Zhu, Shengyu Huang +2
We introduce Rectified Point Flow, a unified parameterization that formulates pairwise point cloud registration and multi-part shape assembly as a single conditional generative pro…