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...
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
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...
By Yuancheng Wei, Linli Yao, Lei Li, Haojie Zhang, Hao Zhou, Fandong Meng, Xu Sun
arXiv:2608. 09111v1 Announce Type: new Abstract: AI video generation has advanced rapidly and entered widespread commercial use.
By Ziheng Jia, Jiaying Qian, Zicheng Zhang, Xiaorong Zhu, Lancheng Gao, Xiongkuo Min
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...
By Shuyue Stella Li, Jacqueline He, Jiahui Chen, Sreya Dutta Roy, Yulia Tsvetkov, Luke Zettlemoyer, Marjan Ghazvininejad, Xiaochuang Han
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.
The paper introduces a test‑time reinforcement learning framework for anomalous video understanding, addressing challenges such as unreliable pseudo‑labels, inadequate reward design, and collapsed group‑relative advantages. It proposes dual‑query consistency filtering, an entropy‑aware consensus reward, and a virtual negative anchor mechanism to improve sample reliability, reward quality, and policy‑gradient signals. Experiments on VAU‑Bench demonstrate significant performance gains, especially on the ECVA subset where accuracy rises from 75.81% to 90.00%.
By Huining Li, Yuxiang Duan, Jiyang Tan, Qian Li, MingCai Chen, Jian Zhang, Xingdong Sheng, Yuntao Du
arXiv:2610.32222v1 Announce Type: new
Abstract: Reinforcement learning has gained attention for improving action-conditioned world models (ACWMs), as it enables reward-driven optimization of visual q...
By Shibo Hong, Siyu Ren, FengJiao Chen, Zhongyuan Peng, Wei Shi, Yixin Cao
RubricRM introduces a pairwise generative reward modeling framework that generates an input‑specific rubric—comprising evaluation dimensions, weights, and scoring criteria—to score candidate images. The method is trained in two stages: supervised fine‑tuning to learn the rubric‑based scoring paradigm and GRPO to refine dimension‑level rewards. Experiments on text‑to‑image generation and instruction‑based image editing benchmarks demonstrate that RubricRM outperforms existing specialized reward models and competes with strong proprietary MLLM judges while using smaller backbones.
By Zijian Kan, Wei Wang, Long Luo, Bing Zhao, Xuan Ren, Weixu Qiao, Wenbo Li, Hu Wei, Lin Qu
VideoGen-Agent is a multimodal agent that uses multitask agentic reinforcement learning to coordinate external tools for video generation. It learns to augment, generate, and verify videos through multi‑turn interactions, guided by prompts and intermediate observations. On the new VABench benchmark, the agent improves base text‑to‑video performance by 19.1 points, and further upgrades to generation tools raise the score to 86.1, with human raters favoring the upgraded configuration in 84.3% of comparisons.
By Binxu Li, Haoyi Duan, Yuhui Zhang, Yaohui Zhang, Zihao Lin, Kaituo Feng, Suozhi Huang, Xiangyi Li, Yu Li, Chunyuan Li, Shilong Liu, Mengdi Wang
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...
By Nai-Xin Zhai, Weihua Cheng, Dexu Yu, Yikai Gu, Hanwen Du, Junchen Fu, Chenxi Huang, Yingwei Song, Liyuan Lillian Ma, Yang Ran, Youhua Li, Yongxin Ni
Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, sp...