Publications (32)
Differential Amplifier-Inspired AmpAttention for Multi-View Robotic Manipulation
Jin Yang, Ping Wei, Nanning Zheng
Multi-view robotic manipulation methods with the attention mechanism have recently achieved significant progress in both training efficiency and task performance. However, the inhe…
Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection
Jin Yang, Ping Wei, Huan Li +1
Video moment retrieval and highlight detection are two highly valuable tasks in video understanding, but until recently they have been jointly studied. Although existing studies ha…
Easily Testable Necessary and Sufficient Algebraic Criteria for Delay-independent Stability of a Class of Neutral Differential Systems
Ping Wei, Qiang Guan, Wensheng Yu +1
This paper analyzes the eigenvalue distribution of neutral differential systems and the corresponding difference systems, and establishes the relationship between the eigenvalue di…
Hyperbolic Multiview Pretraining for Robotic Manipulation
Jin Yang, Ping Wei, Yixin Chen +1
3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embed…
GAWM: Global-Aware World Model for Multi-Agent Reinforcement Learning
Zifeng Shi, Meiqin Liu, Senlin Zhang +3
In recent years, Model-based Multi-Agent Reinforcement Learning (MARL) has demonstrated significant advantages over model-free methods in terms of sample efficiency by using indepe…
Distributed Joint Sensor Registration and Multitarget Tracking Via Sensor Network
Lin Gao, Giorgio Battistelli, Luigi Chisci +1
This paper addresses distributed registration of a sensor network for multitarget tracking. Each sensor gets measurements of the target position in a local coordinate frame, having…