Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.
hub
arXiv preprint arXiv:2310.03739 , year=
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
DiT-Reward converts pretrained DiT models into reward predictors that outperform HPSv3 on four benchmarks while providing 1.65x inference speedup.
DRL trains a discriminator on data versus base-model samples in pretrained representation space and uses its logit as reward in KL-regularized RL, cutting guidance-free FID from 9.38 to 2.62 on SiT and similar gains on other backbones.
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
EAM reformulates adjoint matching for diffusion fine-tuning with linear base drift to allow efficient deterministic sampling and closed-form adjoints while matching or exceeding prior performance.
PAMELA provides a multi-user rating dataset and personalized reward model that predicts individual image preferences more accurately than prior population-level aesthetic models.
DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
STAR uses text-image attention to create dynamic spatial allocation maps that vary across denoising steps and applies the same advantage more strongly to relevant latent regions in RL post-training of diffusion models.
GILC guides discrete diffusion at inference time by adding reward gradients to the prediction logits, matching or beating fine-tuned baselines on DNA, protein, and molecule generation tasks without retraining.
PATHS applies parallel tempering to improve initial particle sampling for SMC reward alignment, yielding better results on layout-to-image and quantity-aware generation tasks.
AdvantageFlow proposes an advantage-weighted forward-process least-squares loss for RL in rectified flow models, stabilized by rollout policy regularization, and reports better image generation performance than Flow-GRPO on Stable Diffusion 3.5.
Derives RAM, a reward-adjusted consistency loss extending diffusion pretraining regression to efficient KL-regularized RL post-training, achieving peak rewards up to 50x faster than Flow-GRPO on Stable Diffusion 3.5M.
Adjoint Matching is derived from the Stochastic Maximum Principle as a Hamiltonian objective whose critical points solve stochastic optimal control problems for generative dynamics.
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
FlowAWR derives an advantage-weighted rectification for optimal velocity fields in flow models, claiming 2-5x faster convergence than DiffusionNFT on SD3.5-Medium.
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
A literature survey that organizes diffusion model alignment methods along five axes (feedback source, reward form, optimization mechanism, distribution shift handling, and explicit safety constraints) and identifies open challenges for reliable deployment.
citing papers explorer
-
Flow-GRPO: Training Flow Matching Models via Online RL
Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.
-
DiT-Reward: Generative Representations for Text-to-Image Reward Modeling
DiT-Reward converts pretrained DiT models into reward predictors that outperform HPSv3 on four benchmarks while providing 1.65x inference speedup.
-
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
DRL trains a discriminator on data versus base-model samples in pretrained representation space and uses its logit as reward in KL-regularized RL, cutting guidance-free FID from 9.38 to 2.62 on SiT and similar gains on other backbones.
-
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
-
Efficient Adjoint Matching for Fine-tuning Diffusion Models
EAM reformulates adjoint matching for diffusion fine-tuning with linear base drift to allow efficient deterministic sampling and closed-form adjoints while matching or exceeding prior performance.
-
Personalizing Text-to-Image Generation to Individual Taste
PAMELA provides a multi-user rating dataset and personalized reward model that predicts individual image preferences more accurately than prior population-level aesthetic models.
-
Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.
-
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
-
STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training
STAR uses text-image attention to create dynamic spatial allocation maps that vary across denoising steps and applies the same advantage more strongly to relevant latent regions in RL post-training of diffusion models.
-
Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction
GILC guides discrete diffusion at inference time by adding reward gradients to the prediction logits, matching or beating fine-tuned baselines on DNA, protein, and molecule generation tasks without retraining.
-
Parallel Tempering Initial Sampling in Inference-Time Reward Alignment
PATHS applies parallel tempering to improve initial particle sampling for SMC reward alignment, yielding better results on layout-to-image and quantity-aware generation tasks.
-
AdvantageFlow: Advantage-Weighted Least Squares for RL in Flow Models
AdvantageFlow proposes an advantage-weighted forward-process least-squares loss for RL in rectified flow models, stabilized by rollout policy regularization, and reports better image generation performance than Flow-GRPO on Stable Diffusion 3.5.
-
Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
Derives RAM, a reward-adjusted consistency loss extending diffusion pretraining regression to efficient KL-regularized RL post-training, achieving peak rewards up to 50x faster than Flow-GRPO on Stable Diffusion 3.5M.
-
Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control
Adjoint Matching is derived from the Stochastic Maximum Principle as a Hamiltonian objective whose critical points solve stochastic optimal control problems for generative dynamics.
-
Improving Video Generation with Human Feedback
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
-
FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
FlowAWR derives an advantage-weighted rectification for optimal velocity fields in flow models, claiming 2-5x faster convergence than DiffusionNFT on SD3.5-Medium.
-
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
-
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
-
Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey
A literature survey that organizes diffusion model alignment methods along five axes (feedback source, reward form, optimization mechanism, distribution shift handling, and explicit safety constraints) and identifies open challenges for reliable deployment.
- DanceOPD: On-Policy Generative Field Distillation