Introduces a Bridge latent interface that maps mismatched student latents into teacher space, enabling distillation from modern diffusion teachers to compact one-step students and raising SD 1.5 HPSv3 from 5.4 to 9.4 while keeping one-step speed.
hub
Hpsv3: Towards wide-spectrum human preference score.arXiv preprint arXiv:2508.03789
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.
ASAP generates over 10K synthetic anatomical preference pairs via targeted degradation of high-fidelity images and applies a localized margin-bounded DPO to reduce anatomical errors in text-to-image human generation, supported by the new HAP dataset and HAF-Bench.
KVPO aligns streaming autoregressive video generators with human preferences via ODE-native GRPO, using KV cache for semantic exploration and TVE for velocity-based policy modeling, yielding gains in quality and alignment.
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.
Formalizes Fashion Detail Generation task, releases FDBench benchmark with 40K+ pairs, and proposes CFAD distillation method plus RL consistency reward that outperforms open-source baselines.
PortraitGen integrates real-image exemplars into GRPO sampling and applies dual rewards (OmniReward and AI-Portrait) to improve photorealism, claiming better results than baselines on a new PortraitBench.
A teacher-student reward model learns reasoning-conditioned score distributions for text-to-image images, yielding ~89% preference accuracy and a 41% net human-preference gain when used for generator optimization.
TextAlign uses a hierarchical VLM reward for preference alignment to boost text accuracy in generative models like FLUX.1-dev.
Proposes HT-GRPO with sketch-then-paint staged updates, prompt-conditioned importance ratios, and hierarchical credit assignment for dMLLMs, reporting gains on GenEval and DPG plus quality metrics.
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
Poly-DPO improves robustness to noisy preference data in visual models, and the new ViPO dataset enables superior performance, with the method reducing to standard DPO on high-quality data.
MT-EditFlow applies flow-matching RL with multi-reward aggregation to improve multi-turn image editing performance on models like FLUX.1-Kontext-dev by 6.85 points at turn-3.
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
GCPO shifts RL policy optimization for flow matching from step-level to chunk-level grouping of consecutive denoising steps, reporting up to 43% relative gains over GRPO on T2I benchmarks and preference tasks.
A training-free method with time-dependent attention gating and trajectory pruning enhances object-background balance in diffusion-based image synthesis.
Empirical study shows reward model ensembles mitigate biases like brightness and composition in preference data for image inpainting, yielding better performance than prior methods without architecture changes.
citing papers explorer
-
Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
Introduces a Bridge latent interface that maps mismatched student latents into teacher space, enabling distillation from modern diffusion teachers to compact one-step students and raising SD 1.5 HPSv3 from 5.4 to 9.4 while keeping one-step speed.
-
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.
-
Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences
ASAP generates over 10K synthetic anatomical preference pairs via targeted degradation of high-fidelity images and applies a localized margin-bounded DPO to reduce anatomical errors in text-to-image human generation, supported by the new HAP dataset and HAF-Bench.
-
KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
KVPO aligns streaming autoregressive video generators with human preferences via ODE-native GRPO, using KV cache for semantic exploration and TVE for velocity-based policy modeling, yielding gains in quality and alignment.
-
Long-Text-to-Image Generation via Compositional Prompt Decomposition
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.
-
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
Formalizes Fashion Detail Generation task, releases FDBench benchmark with 40K+ pairs, and proposes CFAD distillation method plus RL consistency reward that outperforms open-source baselines.
-
PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation
PortraitGen integrates real-image exemplars into GRPO sampling and applies dual rewards (OmniReward and AI-Portrait) to improve photorealism, claiming better results than baselines on a new PortraitBench.
-
Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
A teacher-student reward model learns reasoning-conditioned score distributions for text-to-image images, yielding ~89% preference accuracy and a 41% net human-preference gain when used for generator optimization.
-
TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards
TextAlign uses a hierarchical VLM reward for preference alignment to boost text accuracy in generative models like FLUX.1-dev.
-
Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
Proposes HT-GRPO with sketch-then-paint staged updates, prompt-conditioned importance ratios, and hierarchical credit assignment for dMLLMs, reporting gains on GenEval and DPG plus quality metrics.
-
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
-
ViPO: Visual Preference Optimization at Scale
Poly-DPO improves robustness to noisy preference data in visual models, and the new ViPO dataset enables superior performance, with the method reducing to standard DPO on high-quality data.
-
MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching
MT-EditFlow applies flow-matching RL with multi-reward aggregation to improve multi-turn image editing performance on models like FLUX.1-Kontext-dev by 6.85 points at turn-3.
-
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.
-
Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
GCPO shifts RL policy optimization for flow matching from step-level to chunk-level grouping of consecutive denoising steps, reporting up to 43% relative gains over GRPO on T2I benchmarks and preference tasks.
-
Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
A training-free method with time-dependent attention gating and trajectory pruning enhances object-background balance in diffusion-based image synthesis.
-
Follow-Your-Preference++: Rethinking Preference Alignment for Image Inpainting
Empirical study shows reward model ensembles mitigate biases like brightness and composition in preference data for image inpainting, yielding better performance than prior methods without architecture changes.