Think Before You Score: Thinking Reward Model for Visual Generation

arXiv:2609.37372 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/black-forest-labs/flux

Project page: https://bxhsort.github.io/Thinking-Reward-Model

Terminology

• Benchmark — 33× in this paper · explained in 2 episodes
• Reinforcement Learning — 29× in this paper · explained in 4 episodes
• Alignment — 25× in this paper · explained in 1 episode
• Consistency — 22× in this paper · explained in 3 episodes
• GRPO — 17× in this paper · explained in 6 episodes
• Thinking Reward Model — 11× in this paper
• Accuracy — 10× in this paper · explained in 1 episode
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Failure Modes — 4× in this paper · explained in 3 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Causal Reasoning — 3× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• KL Regularization — 2× in this paper · explained in 2 episodes
• LoRA Adapters — 2× in this paper · explained in 3 episodes
• Prompt Adherence — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Communication Overhead — 1× in this paper · explained in 2 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verifiability — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
• PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
• OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
• Emerging Properties in Unified Multimodal Pretraining
• Leveraging Verifier-Based Reinforcement Learning in Image Editing
• EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation
• ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
• GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation
• Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
• Step1X-Edit: A Practical Framework for General Image Editing
• HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
• RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
• An Evolutionary Agentic Approach for Open-ended Image Quality Perception
• UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
• Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models