arXiv Computer Vision
Nov 6

ArtiVidRM: Verifiable Artifact-as-Rubric Reward Modeling for Explicit Quality Articulation in Video Generation

ArtiVidRM is a new video reward model that first detects visible generation artifacts and compiles them into a structured list, then uses this list as explicit rubrics for quality assessment. By grounding each score in concrete video-level evidence, the model offers a more interpretable and informative reward signal for reinforcement learning. Experiments demonstrate state‑of‑the‑art performance on video preference benchmarks, effective guidance for video diffusion optimization, and the ability to refine closed‑source video generators through artifact‑guided refinement.

By Caorui Li, Yangguang Ji, Shuxia Lin, Yu Chen, YiCheng Xiao, Yongliang Wu, Zhenxiang Jiang, Licheng Tang, Deng Li, Zhuxuanzi Wang, Jiahao Sun, Chonghan Liu, Lirian Su, Jay Wu, Xu Yang
Hugging Face Trending Papers
Aug 10

RAVEN-Eval: Rubric-Guided Automatic Evaluation for AI Video Generation Models Based on LMM Preference Judgement

AI video generation has advanced rapidly and entered widespread commercial use. As a result, quality differences among videos produced by state-of-the-art AI video generation models~(AIVGMs) have become increasingly difficult to discern using conventional evaluation criteria, such as visual fidelity and semantic instruction following.