publications

2026

1. CVPR

   Leveraging Verifier-Based Reinforcement Learning in Image Editing

   Hanzhong Guo, Jie Wu, Jie Liu, Yu Gao, Zilyu Ye, Linxiao Yuan, and 3 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

   Bib PDF

   @inproceedings{guo2026editr1,
     title = {Leveraging Verifier-Based Reinforcement Learning in Image Editing},
     author = {Guo, Hanzhong and Wu, Jie and Liu, Jie and Gao, Yu and Ye, Zilyu and Yuan, Linxiao and Wang, Xionghui and Yu, Yizhou and Huang, Weilin},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     year = {2026},
     eprint = {2604.27505},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

2. arXiv

   UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

   Jie Liu, Zilyu Ye, Linxiao Yuan, Shenhan Zhu, Yu Gao, Jie Wu, and 5 more authors

   arXiv preprint arXiv:2603.23500, 2026

   Bib PDF

   @article{liu2026unigrpo,
     title = {UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation},
     author = {Liu, Jie and Ye, Zilyu and Yuan, Linxiao and Zhu, Shenhan and Gao, Yu and Wu, Jie and Li, Kunchang and Wang, Xionghui and Nie, Xiaonan and Huang, Weilin and Ouyang, Wanli},
     journal = {arXiv preprint arXiv:2603.23500},
     year = {2026},
     eprint = {2603.23500},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

2025

1. arXiv

   Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

   Seedance Team

   arXiv preprint arXiv:2512.13507, 2025

   Bib PDF Website

   @article{seedance2025seedance15pro,
     title = {Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model},
     author = {{Seedance Team}},
     journal = {arXiv preprint arXiv:2512.13507},
     year = {2025},
     eprint = {2512.13507},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

2. arXiv

   RewardDance: Reward Scaling in Visual Generation

   Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, Hanzhong Guo, and 6 more authors

   arXiv preprint arXiv:2509.08826, 2025

   Bib PDF

   @article{wu2025rewarddance,
     title = {RewardDance: Reward Scaling in Visual Generation},
     author = {Wu, Jie and Gao, Yu and Ye, Zilyu and Li, Ming and Li, Liang and Guo, Hanzhong and Liu, Jie and Xue, Zeyue and Hou, Xiaoxia and Liu, Wei and Zeng, Yan and Huang, Weilin},
     journal = {arXiv preprint arXiv:2509.08826},
     year = {2025},
     eprint = {2509.08826},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

3. CVPR

   Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation

   Zilyu Ye, Zhiyang Chen^†, Tiancheng Li, Zemin Huang, Weijian Luo, and Guo-Jun Qi^†

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

   Abs Bib PDF Code

   Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for all prompts. The multi-step reverse diffusion process can be regarded as a kind of chain-of-thought for generating high-quality images step by step. Therefore, diffusion models should reason for each instance to adaptively determine the optimal noise schedule, achieving high generation quality with sampling efficiency. In this paper, we introduce the Time Prediction Diffusion Model (TPDM) for this. TPDM employs a plug-and-play Time Prediction Module (TPM) that predicts the next noise level based on current latent features at each denoising step. We train the TPM using reinforcement learning to maximize a reward that encourages high final image quality while penalizing excessive denoising steps. With such an adaptive scheduler, TPDM not only generates high-quality images that are aligned closely with human preferences but also adjusts diffusion time and the number of denoising steps on the fly, enhancing both performance and efficiency. With Stable Diffusion 3 Medium architecture, TPDM achieves an aesthetic score of 5.44 and a human preference score (HPS) of 29.59, while using around 50% fewer denoising steps to achieve better performance.

   @inproceedings{ye2025scheduleflydiffusiontime,
     title = {Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation},
     author = {Ye, Zilyu and Chen, Zhiyang and Li, Tiancheng and Huang, Zemin and Luo, Weijian and Qi, Guo-Jun},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     year = {2025},
   }

4. arXiv

   Seedance 1.0: Exploring the Boundaries of Video Generation Models

   Yu Gao, Haoyuan Guo, Tuyen Hoang, Weilin Huang, Lu Jiang, Fangyuan Kong, and 38 more authors

   In , 2025

   Bib

   @inproceedings{gao2025seedance10exploringboundaries,
     title = {Seedance 1.0: Exploring the Boundaries of Video Generation Models},
     author = {Gao, Yu and Guo, Haoyuan and Hoang, Tuyen and Huang, Weilin and Jiang, Lu and Kong, Fangyuan and Li, Huixia and Li, Jiashi and Li, Liang and Li, Xiaojie and Li, Xunsong and Li, Yifu and Lin, Shanchuan and Lin, Zhijie and Liu, Jiawei and Liu, Shu and Nie, Xiaonan and Qing, Zhiwu and Ren, Yuxi and Sun, Li and Tian, Zhi and Wang, Rui and Wang, Sen and Wei, Guoqiang and Wu, Guohong and Wu, Jie and Xia, Ruiqi and Xiao, Fei and Xiao, Xuefeng and Yan, Jiangqiao and Yang, Ceyuan and Yang, Jianchao and Yang, Runkai and Yang, Tao and Yang, Yihang and Ye, Zilyu and Zeng, Xuejiao and Zeng, Yan and Zhang, Heng and Zhao, Yang and Zheng, Xiaozheng and Zhu, Peihao and Zou, Jiaxin and Zuo, Feilong},
     year = {2025},
     eprint = {2506.09113},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     url = {https://arxiv.org/abs/2506.09113}
   }

2024

1. arXiv

   Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling

   Zilyu Ye^*, Jinxiu Liu^*, Ruotian Peng^*, Jinjin Cao, Zhiyang Chen, Yiyang Zhang, and 6 more authors

   In arXiv preprint, 2024

   Abs Bib PDF Code

   Recent image generation models excel at creating high-quality images from brief captions. However, they fail to maintain consistency of multiple instances across images when encountering lengthy contexts. This inconsistency is largely due to in existing training datasets the absence of granular instance feature labeling in existing training datasets. To tackle these issues, we introduce Openstory++, a large-scale dataset combining additional instance-level annotations with both images and text. Furthermore, we develop a training methodology that emphasizes entity-centric image-text generation, ensuring that the models learn to effectively interweave visual and textual information. Specifically, Openstory++ streamlines the process of keyframe extraction from open-domain videos, employing vision-language models to generate captions that are then polished by a large language model for narrative continuity. It surpasses previous datasets by offering a more expansive open-domain resource, which incorporates automated captioning, high-resolution imagery tailored for instance count, and extensive frame sequences for temporal consistency. Additionally, we present Cohere-Bench, a pioneering benchmark framework for evaluating the image generation tasks when long multimodal context is provided, including the ability to keep the background, style, instances in the given context coherent. Compared to existing benchmarks, our work fills critical gaps in multi-modal generation, propelling the development of models that can adeptly generate and interpret complex narratives in open-domain environments. Experiments conducted within Cohere-Bench confirm the superiority of Openstory++ in nurturing high-quality visual storytelling models, enhancing their ability to address open-domain generation tasks.

   @inproceedings{ye2024openstorylargescaledatasetbenchmark,
     title = {Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling},
     author = {Ye, Zilyu and Liu, Jinxiu and Peng, Ruotian and Cao, Jinjin and Chen, Zhiyang and Zhang, Yiyang and Xuan, Ziwei and Zhou, Mingyuan and Shen, Xiaoqian and Elhoseiny, Mohamed and Liu, Qi and Qi, Guo-Jun},
     year = {2024},
     eprint = {2408.03695},
     booktitle = {arXiv preprint},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

2. CVPRW

   OpenStory: A Large-Scale Open-Domain Dataset for Subject-Driven Visual Storytelling

   Zilyu Ye^*, Jinxiu Liu^*, JinJin Cao, Zhiyang Chen, Ziwei Xuan, Mingyuan Zhou, and 2 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

   Abs Bib PDF

   Recently, the advancement and evolution of generative AI have been highly compelling. In this paper, we present OpenStory, a large-scale dataset tailored for training subject-focused story visualization models to generate coherent and contextually relevant visual narratives. Addressing the challenges of maintaining subject continuity across frames and capturing compelling narratives, We propose an innovative pipeline that automates the extraction of keyframes from open-domain videos. It ingeniously employs vision-language models to generate descriptive captions, which are then refined by a large language model to ensure narrative flow and coherence. Furthermore, advanced subject masking techniques are applied to isolate and segment the primary subjects. Derived from diverse video sources, including YouTube and existing datasets, OpenStory offers a comprehensive open-domain resource, surpassing prior datasets confined to specific scenarios. With automated captioning instead of manual annotation, high-resolution imagery optimized for subject count per frame, and extensive frame sequences ensuring consistent subjects for temporal modeling, OpenStory establishes itself as an invaluable benchmark. It facilitates advancements in subject-focused story visualization, enabling the training of models capable of comprehending and generating intricate multi-modal narratives from extensive visual and textual inputs.

   @inproceedings{ye2024openstory,
     title = {OpenStory: A Large-Scale Open-Domain Dataset for Subject-Driven Visual Storytelling},
     author = {Ye, Zilyu and Liu, Jinxiu and Cao, JinJin and Chen, Zhiyang and Xuan, Ziwei and Zhou, Mingyuan and Liu, Qi and Qi, Guo-Jun},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {7953--7962},
     year = {2024},
   }