#gflownet2 articles

2 articles

AINeutralarXiv – CS AI · 6h ago1

🧠

Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training

Researchers propose RapTB, a new training objective for Generative Flow Networks (GFlowNets) that addresses mode collapse issues in fine-tuning large language models. The method includes a submodular replay strategy (SubM) and demonstrates improved performance in molecule generation tasks while maintaining diversity and validity.

AINeutralarXiv – CS AI · 6h ago0

🧠

Learning Shortest Paths with Generative Flow Networks

Researchers present a novel framework using Generative Flow Networks (GFlowNets) to solve shortest path problems in graphs. The method proves that minimizing total flow forces GFlowNets to traverse only shortest paths, demonstrating competitive performance in pathfinding tasks including solving Rubik's Cubes with smaller search budgets than existing approaches.