MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators
cs.AI, cs.CE, cs.CV
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/HaCTang/MeanFlowAdvantage
Terminology
Sources
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- $R_\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation
- AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
- Reinforcing Few-step Generators via Reward-Tilted Distribution Matching
- MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
- AdvantageFlow: Regularized Advantage-Weighted RL in Flow Models
- Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
- Riemannian MeanFlow
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection