Jiyuan Wang

Jiyuan Wang   王纪元

I am a third-year joint Ph.D. (Bachelor-straight-to-doctorate) student at Beijing Jiaotong University (BJTU) and Nanyang Technological University (NTU).

I conduct research at MePro (led by Prof. Yao Zhao) and S-Lab, jointly supervised by Prof. Chunyu Lin and Prof. Guosheng Lin.

Prior to that, I received my undergraduate degree in Computer Science and Technology from BJTU.

✉   wangjiyuan@bjtu.edu.cn ◎   Google Scholar ◉   GitHub

Research Interests

My research interests focus on AIGC, especially video generation and editing. I am enthusiastic about exploring generative models and tools such as Diffusion, FLUX, Flow Matching, and VLMs, and successfully integrating them into my research to achieve impressive results.

1) AIGC: Video Generation/Editing, Diffusion Model, Flow Matching, DiffusionNFT, GRPO (Generative)

2) VLM: Video Understanding, GRPO, Reward Model

3) Others: 3D Gaussian, Depth Estimation, Normal Estimation

Publications

(Orange title indicates first/co-first author)
Preprint
Dandelion overview figure
Dandelion: Towards Real-time and Consistent Long Video Depth Estimation
Zeyang Chen†, Jiyuan Wang†, Jianhai Du, Lang Nie, Dewen Fan, Boheng Zhang, Fan Yang, Fei Zuo, Chunyu Lin
Under Review
WritingPhysBench overview figure
WritingPhysBench: Evaluating Handwriting Physical Plausibility in Text-to-Video Generation
Xinyao Ruan†, Jiyuan Wang†, Xingyu Qi, Jiashu Yang, Yuan Zhang, Guosheng Lin, Dewen Fan, Boheng Zhang, Huan Ouyang, Fei Zuo, Zijun Li, Junlong Wu, Huaiqing Wang, Jia Sun, Fan Yang, Chunyu Lin
Under Review
CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating teaser
CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
Jiyuan Wang, Huan Ouyang, Jiuzhou Lin, Chunyu Lin, Dewen Fan, Boheng Zhang, Haonan Fan, Fei Zuo, Jia Sun, Huaiqing Wang, Honglie Wang, Yiyang Fan, Zhenlong Yuan, Zijun Li, Yongrui Heng, Guosheng Lin, Fan Yang
Under Review
[Paper]
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools teaser
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
Zhenlong Yuan, Rongbin Tan, Kejin Cui, Min Qiu, Fangfang Lin, Mengmeng Wang, Yi Wang, Zijian Song, Zhiyuan Wang, Jiyuan Wang, Yue Wang, Shuhan Song, Huawei Cao
Under Review
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation teaser
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
Zijun Li, Yimin Zhou, Jia Sun, Honglie Wang, Pengcheng Wei, Junlong Wu, Yongrui Heng, Jiyuan Wang, Huan Ouyang, Boheng Zhang, Huaiqing Wang, Dewen Fan, Qianqian Gan, Fan Yang, Tingting Gao
Under Review
CoFiRender: Rewarding Coarse-to-Fine Quality for Visual Text Rendering in Image Editing teaser
CoFiRender: Rewarding Coarse-to-Fine Quality for Visual Text Rendering in Image Editing
Honglie Wang, Jia Sun, Zijun Li, Junlong Wu, Pengcheng Wei, Jiyuan Wang, Boheng Zhang, Huaiqing Wang, Dewen Fan, Qianqian Gan, Fan Yang, Tingting Gao, Yan-Ming Zhang
Under Review
2026
Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing teaser
Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing
Jiyuan Wang, Chunyu Lin, Lei Sun, Zhi Cao, Yuyang Yin, Lang Nie, Zhenlong Yuan, Xiangxiang Chu, Yunchao Wei, Kang Liao, Guosheng Lin
European Conference on Computer Vision (ECCV), 2026
[Paper] [Project Page] [Code]
Releasing Perspective Priors for 360° Depth Estimation via Self-Conditioned Modulation teaser
Releasing Perspective Priors for 360° Depth Estimation via Self-Conditioned Modulation
Cheng Guan, Chunyu Lin, Zhijie Shen, Junsong Zhang, Jiyuan Wang
European Conference on Computer Vision (ECCV), 2026
[Paper]
From Editor to Dense Geometry Estimator teaser
From Editor to Dense Geometry Estimator
Jiyuan Wang, Chunyu Lin, Lei Sun, Rongying Liu, Lang Nie, Mingxing Li, Kang Liao, Xiangxiang Chu, Yao Zhao
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
[Project Page] [Paper] [Code]
Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation teaser
Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation
Wenbo Nie, Lang Nie, Chunyu Lin, Jingwen Chen, Ke Xing, Jiyuan Wang, Kang Liao
AAAI Conference on Artificial Intelligence (AAAI), 2026
[Paper] [Video]
2025
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation teaser
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
Jiyuan Wang, Chunyu Lin, Cheng Guan, Lang Nie, Jing He, Haodong Li, Kang Liao, Yao Zhao
Conference on Neural Information Processing Systems (NeurIPS), 2025
[Paper] [Project Page] [Code]
DRL4AOI: A DRL Framework for Semantic-aware AOI Segmentation in Location-Based Services teaser
DRL4AOI: A DRL Framework for Semantic-aware AOI Segmentation in Location-Based Services
Youfang Lin, Jinji Fu, Haomin Wen, Jiyuan Wang, Zhenjie Wei, Yuting Qiang, Xiaowei Mao, Liaxia Wu, Haoyuan Hu, Yuxuan Liang, Huaiyu Wan
ACM Transactions on Intelligent Systems and Technology (TIST), 2025
[Paper] [Code]
Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline teaser
Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline
Zhihao Zhang, Chunyu Lin, Lang Nie, Jiyuan Wang, Meiqin Liu
IEEE Transactions on Intelligent Transportation Systems (TITS), 2025
[Paper]
2024
Digging into contrastive learning for robust depth estimation with diffusion models teaser
Digging into contrastive learning for robust depth estimation with diffusion models
Jiyuan Wang, Chunyu Lin, Lang Nie, Kang Liao, Shuwei Shao, Yao Zhao
ACM Multimedia (ACM MM), 2024
[Paper] [Code]
WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions teaser
WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions
Jiyuan Wang, Chunyu Lin, Lang Nie, Shujun Huang, Yao Zhao, Xing Pan, Rui Ai
IEEE International Conference on Robotics and Automation (ICRA), 2024
[Paper] [Code]
OverleafCopilot: Empowering academic writing in Overleaf with large language models teaser
OverleafCopilot: Empowering academic writing in Overleaf with large language models
Haomin Wen, Zhenjie Wei, Yan Lin, Jiyuan Wang, Yuxuan Liang, Huaiyu Wan
Web Application (4000+ Users)
[Paper] [Main Page]

† Equal contribution (co-first authors).

Experiences

Amap, Alibaba — DreamX Team

Algorithm Engineer Intern · Machine Learning R&D
Apr. 2025 — Nov. 2025
Dense prediction for generation/editing models and reinforcement learning for generation. Mentors: Lei Sun and Xiangxiang Chu.

Xiaomi

Algorithm Engineer Intern
Sep. 2024 — Mar. 2025
Geometric perception for generative models.

Selected Awards

Academic Service & Activities

Frequent Reviewer