MEND: RL For Flow Models via Proximal Velocity Matching
cs.LG, cs.CV
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Fine-Tuning Diffusion Models via Intermediate Distribution Shaping
- Universal Guidance for Diffusion Models
- ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration
- Training Diffusion Models with Reinforcement Learning
- Diffusion Posterior Sampling for General Noisy Inverse Problems
- Directly Fine-Tuning Diffusion Models on Differentiable Rewards
- Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
- RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization
- DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
- DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
- FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
- GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
- Manifold Preserving Guided Diffusion
- Reward-guided Fine-Tuning of One-Step Generative Models via Wasserstein Gradient Flow
- Distribution Matching Distillation Meets Reinforcement Learning
- Drifting Preference Optimization for One-Step Generative Models
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
- Diffusion Alignment as Variational Expectation-Maximization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks