arXiv (All)
open access
$λ$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource
Reinforcement learning is increasingly used to align image generators with reward signals, and Flow-GRPO recently extended this paradigm to flow-matching models by treating the denoising sampler as a stochastic policy that can be optimized from reward feedback. Training in this setting is unstable i
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- $λ$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource#1006836
- Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching#927580
- Multi-Marginal Flow Matching with Adversarially Learnt Interpolants#799890
- DGLight: DQN-Guided GRPO Fine-Tuning of Large Language Models for Traffic Signal Control#141511
- QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning#1128766
Record · ID 1036451
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive