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 ...
GitHub

PDF Diff Viewer, a side-by-side, visual highlight, sync-scroll, PDF comparer, written in Python. Open source, mostly powered by PyMuPDF and Tkinter. Optional support for git ...

Windows binaries are provided; while no installation is needed, you need to decompress everything and then run "pdf_viewer_app.exe" within the folder "pdf_viewer_app". Make sure you have writing ...
IEEE

Cooperative Algorithms for Multi-Agent Multi-Armed Bandits: Integrating $\varepsilon$-Greedy Optimization

Abstract: The multi-armed bandit framework is a wellestablished learning paradigm that enables sequential decisionmaking under uncertainty. This framework has been widely applied in various domains, ...
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 ...