arxiv
PublishedMay 29, 2026 at 4:00 AM
—neutral
Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
Publisher summary· verbatim
arXiv:2603.00454v2 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) enable fine-tuning large language models to approximate reward-proportional posteriors, but they remain prone to mode collapse, manifesting as prefix collapse and length bias. We attribute this to two fact
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning9harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning9harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models9harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents9hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗