activity
20242026
collaborators

13 papers

cs.RO2026

Rectified Schrödinger Bridge Matching for Few-Step Visual Navigation

Wuyang Luan, Junhui Li, Weiguang Zhao +3

Visual navigation is a core challenge in Embodied AI, requiring autonomous agents to translate high-dimensional sensory observations into continuous, long-horizon action trajectori…

cs.RO2026

Towards Robotic Dexterous Hand Intelligence: A Survey

Weiguang Zhao, Tian Liang, Xihao Guo +3

Robotic dexterous hands are central to contact-rich manipulation, with rapid progress driven by advances in hardware, sensing, control, simulation, and data generation. However, ex…

cs.CV2026

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation

Wuyang Luan, Junhui Li, Weiguang Zhao +3

Vision-Language-Action (VLA) models based on flow matching -- such as pi0, pi0.5, and SmolVLA -- achieve state-of-the-art generalist robotic manipulation, yet their iterative denoi…

cs.RO2026

Tele-Catch: Adaptive Teleoperation for Dexterous Dynamic 3D Object Catching

Weiguang Zhao, Junting Dong, Rui Zhang +3

Teleoperation is a key paradigm for transferring human dexterity to robots, yet most prior work targets objects that are initially static, such as grasping or manipulation. Dynamic…

cs.CV2026

TrajVG: 3D Trajectory-Coupled Visual Geometry Learning

Xingyu Miao, Weiguang Zhao, Tao Lu +5

Feed-forward multi-frame 3D reconstruction models often degrade on videos with object motion. Global-reference becomes ambiguous under multiple motions, while the local pointmap re…

cs.CV2026

SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking

Weiguang Zhao, Haoran Xu, Xingyu Miao +11

Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward ge…