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
Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 2
citation-polarity summary
verdicts
UNVERDICTED 11representative citing papers
STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
DiRotQ uses PCA-based rotation-aware activation quantization combined with GPTQ to achieve better FID and PSNR in 4-bit diffusion transformers than prior methods like SVDQuant.
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
DiT-ST converts complete-text captions into split-text primitives via LLMs and injects them hierarchically across denoising stages to reduce semantic confusion in DiT-based text-to-image generation.
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.
-
STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
-
Step-level Denoising-time Diffusion Alignment with Multiple Objectives
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
-
Joint Relational Database Generation via Graph-Conditional Diffusion Models
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
-
DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
DiRotQ uses PCA-based rotation-aware activation quantization combined with GPTQ to achieve better FID and PSNR in 4-bit diffusion transformers than prior methods like SVDQuant.
-
Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
-
Intermediate Representations are Strong AI-Generated Image Detectors
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
-
Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
-
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.
-
Scaling Properties of Continuous Diffusion Spoken Language Models
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
-
Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
DiT-ST converts complete-text captions into split-text primitives via LLMs and injects them hierarchically across denoising stages to reduce semantic confusion in DiT-based text-to-image generation.