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
Flux.https://github.com/black-forest-labs/flux
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.CV 12verdicts
UNVERDICTED 12representative citing papers
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
Asymmetric Flow Modeling restricts noise prediction to a low-rank subspace for high-dimensional flow generation, reaching 1.57 FID on ImageNet 256x256 and new state-of-the-art pixel text-to-image performance via finetuning from latent models.
G²TR reduces visual tokens and prefill computation by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency while preserving reasoning accuracy and editing quality.
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
LatentHDR generates structurally consistent panoramic HDR images by producing one scene latent with a diffusion backbone then deterministically mapping it to multiple exposure latents via a lightweight conditional head.
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.
Prior-Aligned AutoEncoders shape latent manifolds with spatial coherence, local continuity, and global semantics to improve latent diffusion, achieving SOTA gFID 1.03 on ImageNet 256x256 with up to 13x faster convergence.
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
PermuQuant reduces per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same groups using a calibration-checked permutation.
Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.
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.
-
ImageAttributionBench: How Far Are We from Generalizable Attribution?
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
-
Asymmetric Flow Models
Asymmetric Flow Modeling restricts noise prediction to a low-rank subspace for high-dimensional flow generation, reaching 1.57 FID on ImageNet 256x256 and new state-of-the-art pixel text-to-image performance via finetuning from latent models.
-
G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
G²TR reduces visual tokens and prefill computation by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency while preserving reasoning accuracy and editing quality.
-
Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
-
LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR
LatentHDR generates structurally consistent panoramic HDR images by producing one scene latent with a diffusion backbone then deterministically mapping it to multiple exposure latents via a lightweight conditional head.
-
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.
-
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
Prior-Aligned AutoEncoders shape latent manifolds with spatial coherence, local continuity, and global semantics to improve latent diffusion, achieving SOTA gFID 1.03 on ImageNet 256x256 with up to 13x faster convergence.
-
DanceGRPO: Unleashing GRPO on Visual Generation
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
-
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
PermuQuant reduces per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same groups using a calibration-checked permutation.
-
Show-o2: Improved Native Unified Multimodal Models
Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.