OP-GRPO is the first off-policy GRPO method for flow-matching models that reuses trajectories via replay buffer and importance sampling corrections, matching on-policy performance with 34.2% of the training steps.
arXiv preprint arXiv:2510.22319 (2025) 3
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
years
2026 9representative citing papers
EAM speeds up adjoint matching for diffusion model reward fine-tuning by switching to linear base drift, allowing deterministic few-step solvers and closed-form adjoints with up to 4x faster convergence on text-to-image benchmarks.
GDMD replaces raw-sample rewards with distillation-gradient rewards in RL-guided diffusion distillation, yielding 4-step models that surpass their multi-step teachers on GenEval and human preference metrics.
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
V-GRPO makes ELBO surrogates stable and efficient for online RL alignment of denoising models, delivering SOTA text-to-image performance with 2-3x speedups over MixGRPO and DiffusionNFT.
Reward Score Matching unifies reward-based fine-tuning for flow and diffusion models by recasting alignment as score matching to a value-guided target.
Qwen-Image-2.0 unifies high-fidelity image generation and precise editing by coupling Qwen3-VL with a Multimodal Diffusion Transformer, improving text rendering, photorealism, and complex prompt following over prior versions.
citing papers explorer
-
OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models
OP-GRPO is the first off-policy GRPO method for flow-matching models that reuses trajectories via replay buffer and importance sampling corrections, matching on-policy performance with 34.2% of the training steps.
-
Efficient Adjoint Matching for Fine-tuning Diffusion Models
EAM speeds up adjoint matching for diffusion model reward fine-tuning by switching to linear base drift, allowing deterministic few-step solvers and closed-form adjoints with up to 4x faster convergence on text-to-image benchmarks.
-
Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
GDMD replaces raw-sample rewards with distillation-gradient rewards in RL-guided diffusion distillation, yielding 4-step models that surpass their multi-step teachers on GenEval and human preference metrics.
-
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.
-
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
-
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
V-GRPO makes ELBO surrogates stable and efficient for online RL alignment of denoising models, delivering SOTA text-to-image performance with 2-3x speedups over MixGRPO and DiffusionNFT.
-
Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
Reward Score Matching unifies reward-based fine-tuning for flow and diffusion models by recasting alignment as score matching to a value-guided target.
-
Qwen-Image-2.0 Technical Report
Qwen-Image-2.0 unifies high-fidelity image generation and precise editing by coupling Qwen3-VL with a Multimodal Diffusion Transformer, improving text rendering, photorealism, and complex prompt following over prior versions.
- TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment