arXiv Computer Vision
When Pairwise Preferences Cycle: A Reliability-Anchored Preference Walk for Video GRPO
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Sep 19
RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video reward models often produce unstable sc...
arXiv Computer Vision
Sep 22
RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
arXiv:2609.22947v1 Announce Type: new Abstract: Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, exist...
arXiv AI
Aug 25
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation
arXiv:2608.21425v1 Announce Type: cross Abstract: Video generation is central to AI-powered content creation. Aligning generated videos with human preferences is a key criterion for evaluating genera...
arXiv AI
Oct 15
IsoVRBench: Video Reward Modeling Without Human Feedback
arXiv:2610.17234v1 Announce Type: new Abstract: Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignme...
arXiv Computer Vision
Aug 21
VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation
arXiv:2608. 18607v2 Announce Type: replace Abstract: Using reinforcement learning to post-train joint video-audio generation models requires a reward signal.
arXiv Computer Vision
Sep 7
Step Back to Move Forward: Reflection-Aware Preference Optimization for Visual Generation
The paper introduces Reflection-Aware GRPO (RA‑GRPO), a reinforcement‑learning framework that aligns diffusion generative models with human preferences. It uses Diffusion Reflection to correct intermediate sampling paths by reversing the diffusion process, and Counterfactual Path Synthesis to embed these corrected trajectories into the policy, avoiding extra inference cost. Experiments on text‑to‑image and text‑to‑video models show RA‑GRPO outperforms existing methods, reducing reward hacking and improving generalization while remaining architecture‑agnostic.