Scientific Research Publishing

Geo-Refined Point Transformer: Coordinate-Aware Excitation and Positional Upsampling for 3D Scene Segmentation ()

The proposed Coordinate-Aware Feature Excitation (CAFE) module and Position-Aware Upsampling (Pos-Up) module both adhere to ...
IEEE

Graph Linear Convolution Pooling for Learning in Incomplete High-Dimensional Data

Abstract: High-dimensional and incomplete (HDI) data are frequently encountered in diverse real-world applications involving complex interactions among numerous nodes. Approaches based on latent ...
IEEE

Lyapunov Functions for Switched Linear Systems: Proof of Convergence for an LP Computational Approach

Abstract: A recent approach uses linear programming (LP) to compute continuous and piecewise affine (CPA) Lyapunov functions for arbitrary switched linear systems. Such a Lyapunov function is a common ...
GitHub

Improving Policy-Conditioned Value Functions

Current Actor-Critic Reinforcement Learning algorithms face a fundamental limitation. The critic has to implicitly learn about the current state of the policy embodied by the actor. This in turn leads ...