← Back to all news
arXiv Computer Vision By Yibin Wang, Zehan Wang, Junshu Tang, Zhimin Li, Yujie Zhou, Jiazi Bu, Pengyang Ling, Feng Han, Zhixiong Zhang, Long Xing, Shengyuan Ding, Ziang Li, Cheng Jin, Yuhang Zang, Jiaqi Wang, Tianyu Pang

WorldReward: Reward Modeling for Camera-Conditioned World Models

Read the original on arXiv Computer Vision →

WorldReward introduces a vision‑language model–based reward system for camera‑conditioned world models, combining action consistency and visual quality evaluation. It processes paired videos by splitting them into action‑aligned chunks, structuring visual evidence, and aggregating decisions through voting. The model is trained on a large, reasoning‑augmented preference dataset and outperforms GPT‑5.5 on a human‑annotated benchmark, improving both action execution and visual quality when applied to RL post‑training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 10

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

VideoTIR introduces a reinforcement‑learning approach to improve long‑video understanding by encouraging multimodal large language models to use comprehensive multi‑level toolkits efficiently. It combines Zero‑RL and SFT cold‑starting strategies to help models retrieve and focus on meaningful video segments, images, and regions, thereby reducing hallucinations. The method includes Toolkit Action Grouped Policy Optimization (TAGPO) to streamline tool‑calling and a sandbox‑based trajectory synthesis framework for high‑quality data, achieving strong results on three long‑video QA benchmarks.

By Zhe Gao, Shiyu Shen, Taifeng Chai, Weinong Wang, Haotian Xu, Xing Wu, Wenbin Li, Qi Fan, Yang Gao, Dacheng Tao
llmsreinforcement-learningfine-tuningmultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
Oct 9

WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation

WorldAlign introduces a decoupled 4D reward framework for improving world consistency in generated videos. It separates static regions from dynamic subjects, aligning each with a suitable world prior—geometric priors for static geometry and a vision‑language model for dynamic subjects—using masked reprojection and a VLM‑as‑a‑judge reward. The method enhances both static and dynamic consistency in pretrained image‑to‑video generators without relying on human preference data.

By Jing He, Kaixin Ding, Xingye Tian, Guibao Shen, Wenhang Ge, Xin Tao, Pengfei Wan, Ying-Cong Chen
llmsdiffusionmultimodalsafety
More like this →
arXiv Computer Vision
Aug 27

PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment

PreResQ‑R1 introduces a Preference‑Response Disentangled Reinforcement Learning framework for Visual Quality Assessment that jointly optimizes absolute score regression and relative ranking consistency. It employs a dual‑branch reward system—modeling intra‑sample response coherence and inter‑sample preference alignment—trained with Group Relative Policy Optimization. The method extends to video quality assessment via a global‑temporal and local‑spatial data flow strategy, achieving state‑of‑the‑art results on 10 IQA and 5 VQA benchmarks with only 6K images and 28K videos, and provides human‑aligned reasoning traces.

By Zehui Feng, Weichuan Wang, Xiaohan Chen, Ting Han
llmsreinforcement-learningfine-tuningmultimodalbenchmarkssafety
More like this →