FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods. Existing density-approximated policy gradient methods rely on stochastic SDE samplers to construct tractable transition kernels, which introduce training-inference inconsistencies and necessitates Classifier-Free Guidance (CFG). While implicit frameworks such as DiffusionNFT directly optimize forward-process velocity fields, its heuristic fixed-magnitude corrections prevent optimization strength from relative intra-group quality. We propose \textit{Flow Advantage-Weighted Rectification} (\textbf{FlowAWR}), a paradigm that recasts continuous generativ...
| Authors | Zheming Fu, Ruizhe He, Wei Shang et al. |
|---|---|
| Primary category | cs.LG |
| Published | 29 June 2026 |
| Last updated at source | 9 October 2026 |
Connected in the knowledge graph
- simuler/GraftSet-VideoDataset · cited by
Models and datasets referencing this paper
- simuler/GraftSet-VideoDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.