arXiv AI
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
4d ago
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
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 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 AI
Oct 1
Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
arXiv:2605.07872v2 Announce Type: replace-cross Abstract: Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains s...
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 AI
Sep 30
CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models
CoRe introduces a co‑evolving reward framework to mitigate latent reward hacking in video diffusion models. By continuously refitting the latent‑reward model on the generator’s current samples and anchoring it to real‑video preferences, CoRe prevents the generator from drifting outside the reward model’s training support. Experiments on Wan2.1‑T2V‑1.3B demonstrate that CoRe improves generation quality over pretrained models and prior alignment methods while avoiding quality collapse.