AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
hub Mixed citations
Imagereward: Learning and evaluating human preferences for text-to-image generation
Mixed citation behavior. Most common role is background (33%).
15
Pith papers citing it
Background
33% of classified citations
hub tools
citation-role summary
background 2
baseline 2
method 2
citation-polarity summary
representative citing papers
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
ArenaPO infers Gaussian capability distributions from pairwise preferences and applies truncated-normal latent inference to derive fine-grained offline rewards for preference optimization of text-to-image diffusion models.
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
A hierarchical variational formulation amortizes test-time guidance in diffusion models to achieve strong quality-speed tradeoffs with significantly reduced inference compute.
CPC-VAR adds Gradient-based Concept Neuron Selection for continual single-concept learning and a context-aware multi-branch composition strategy to reduce forgetting and entanglement in VAR-based personalized image generation.
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.
Auto-Rubric as Reward externalizes VLM preferences into structured rubrics and applies Rubric Policy Optimization to create more reliable binary rewards for multimodal generation, outperforming pairwise models on text-to-image and editing benchmarks.
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
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.
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.
Diff.-NPO frames diffusion alignment as a self-play game reaching Nash equilibrium and reports better text-to-image results than prior DPO-style methods.
A post-training pipeline for video generation models combines SFT, RLHF with novel GRPO, prompt enhancement, and inference optimization to improve visual quality, temporal coherence, and instruction following.
citing papers explorer
-
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
-
LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
-
Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models
ArenaPO infers Gaussian capability distributions from pairwise preferences and applies truncated-normal latent inference to derive fine-grained offline rewards for preference optimization of text-to-image diffusion models.
-
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
-
Hierarchical Variational Policies for Reward-Guided Diffusion
A hierarchical variational formulation amortizes test-time guidance in diffusion models to achieve strong quality-speed tradeoffs with significantly reduced inference compute.
-
CPC-VAR:Continual Personalized and Compositional Generation in Visual Autoregressive Models
CPC-VAR adds Gradient-based Concept Neuron Selection for continual single-concept learning and a context-aware multi-branch composition strategy to reduce forgetting and entanglement in VAR-based personalized image generation.
-
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.
-
Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
Auto-Rubric as Reward externalizes VLM preferences into structured rubrics and applies Rubric Policy Optimization to create more reliable binary rewards for multimodal generation, outperforming pairwise models on text-to-image and editing benchmarks.
-
Stream-T1: Test-Time Scaling for Streaming Video Generation
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
-
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.
-
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.
-
Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
Diff.-NPO frames diffusion alignment as a self-play game reaching Nash equilibrium and reports better text-to-image results than prior DPO-style methods.
-
A Systematic Post-Train Framework for Video Generation
A post-training pipeline for video generation models combines SFT, RLHF with novel GRPO, prompt enhancement, and inference optimization to improve visual quality, temporal coherence, and instruction following.
- CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
- SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models