SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO

arXiv:2609.32340 · cs.CV · Submitted 2026-09-26 · Read on arXiv

cs.CV

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/Yunkai-Yang/sga_flow_grpo

Terminology

• GRPO — 78× in this paper · explained in 6 episodes
• Credit assignment — 36× in this paper · explained in 3 episodes
• Alignment — 18× in this paper · explained in 1 episode
• Tokenization — 13× in this paper · explained in 2 episodes
• Reward Function — 10× in this paper · explained in 2 episodes
• Diffusion Model — 9× in this paper · explained in 8 episodes
• Reinforcement Learning — 9× in this paper · explained in 4 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Diffusion Models — 7× in this paper · explained in 6 episodes
• Generative Model — 5× in this paper · explained in 2 episodes
• Generative Models — 5× in this paper · explained in 2 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Classifier-Free Guidance — 3× in this paper
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Computational overhead — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Flow Matching Model — 2× in this paper · explained in 2 episodes
• International Conference on Computer Vision — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Median Absolute Deviation — 2× in this paper
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Active Regions — 1× in this paper · explained in 1 episode
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes

Sources

• Dense Reward for Free in Reinforcement Learning from Human Feedback
• SkyReels-V2: Infinite-length Film Generative Model
• Classifier-Free Diffusion Guidance
• GPT-4o System Card
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
• Video Diffusion Alignment via Reward Gradients
• Stepwise Credit Assignment for GRPO on Flow-Matching Models
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
• DanceGRPO: Unleashing GRPO on Visual Generation

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