IEEE

AVTP-Based CAN-TSN Scheduling Through Constructive Heuristic and Hybrid Iterative Greedy Algorithm for High-Load Automotive Network

Abstract: In modern automotive zonal electrical/electronic architectures, Time-Sensitive Networking (TSN) serves as the communication backbone, while Controller Area Network (CAN) operates as regional ...
GitHub

A comprehensive implementation of self-supervised reinforcement learning algorithms including contrastive learning, predictive models, and representation learning for RL tasks.

Self-supervised reinforcement learning is a technique where agents learn useful representations and skills from the environment through self-generated tasks, such as predicting next states or learning ...
IEEE

Target Controllability of Complex Networks Based on Greedy Optimization

Abstract: Controlling large complex networks is a common and important problem. In the field of network control, controlling target nodes is more efficient and feasible than controlling all nodes to ...
GitHub

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

We propose TraceRL, a trajectory-aware reinforcement learning method for diffusion language models, which demonstrates the best performance among RL approaches for DLMs. We also introduce a ...