Jinhu Lu

TL;DR: The Synchronous Spatio-Temporal grAph Transformer (S²TAT) network is proposed for efficiently modeling the traffic data and a novel attention-based strategy is introduced in the output module, being able to capture more valuable historical information to overcome the shortcoming of conventional average aggregation.

TL;DR: This paper develops other type of controllers for follower agents: utilizing the properties of rooted graphs, one is able to design linear controllers incorporating relative positions between the follower agents and their neighbors, to stabilize the overall large formations.

TL;DR: This brief investigates parameter identification of a memristor-based chaotic system (proposed by Muthuswamy in 2010) and shows that the proposed parameter identification methods are effective.

TL;DR: A normalized Nash equilibrium seeking algorithm is presented to solve the proposed power allocation problem in a distributed way and combines Lyapunov stability with the singular perturbation analysis, the convergence of the proposed algorithm is analyzed.

TL;DR: This paper proposes an efficient end-to-end pruning method based on feature stabilization (EPFS), which is feasible to be implemented for structured pruning such as filter pruning and block pruning, and introduces the Center Loss to stabilize the deep feature and fast iterative shrinkage-thresholding algorithm (FISTA) to accelerate the convergence of mask.