Jing Wang (王晶)

I am currently a second-year PhD student at the Sun Yat-sen University, advised by Prof. Xiaodan Liang. Currently, I intern at Kuaishou (Kling AI), focusing on Diffusion Models, Multimodal Models, Generative Models, and Reinforcement learning for Visual Generation.

Email  /  Google Scholar  /  Github  / 

profile photo
Education

  • University of Science and Technology Beijing, Sept. 2017 - Jun. 2021, B.S. in School of Automation.
  • University of Science and Technology Beijing, Sept. 2021 - Jun. 2024, M.S. in School of Automation.
  • Sun Yat-sen University, Sept. 2024 - Jun. 2028, Ph.D. in School of Intelligent Systems Engineering.
  • News

  • One paper (Co-first author) about controlable image generation is accepted by AAAI 2026.
  • One paper (First author) about physical-aware text-to-video generation is accepted by NeurIPS 2025 (Spotlight).
  • One paper about story synthesis is accepted by ICCV 2025.
  • One paper (First author) about efficent video generation is accepted by ICLR 2025.
  • One paper (First author) about few-shot segmentation is accepted by AAAI 2024.
  • Publications

    * indicates equal contribution

    GRPO-Guard GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
    Jing Wang, Jiajun Liang, Jie Liu, Henglin Liu, Gongye Liu, Jun Zheng, Wanyuan Pang, Ao Ma, Zhenyu Xie, Xintao Wang, Meng Wang, Pengfei Wan, Xiaodan Liang
    Preprint
    arXiv / Code / Project Page / BibTeX
    Relactrl Relactrl: Relevance-guided efficient control for diffusion transformers
    Ke Cao*, Jing Wang*, Ao Ma, Jiasong Feng, Zhanjie Zhang, Xuanhua He, Shanyuan Liu, Bo Cheng, Dawei Leng, Yuhui Yin, Jie Zhang
    AAAI 2026
    arXiv / Code / Project Page / BibTeX
    WISA WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation
    Jing Wang, Ao Ma, Ke Cao, Jun Zheng, Zhanjie Zhang, Jiasong Feng, Shanyuan Liu, Yuhang Ma, Bo Cheng, Dawei Leng, Yuhui Yin, Xiaodan Liang
    NeurIPS 2025 Spotlight
    arXiv / Code / Project Page / BibTeX
    PT-T2I/V PT-T2I/V: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Image/Video-Task
    Jing Wang, Ao Ma, Jiasong Feng, Dawei Leng, Yuhui Yin, Xiaodan Liang
    ICLR 2025
    arXiv / Code / Project Page / BibTeX
    Adaptive FSS Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement
    Jing Wang, Jiangyun Li, Chen Chen, Yisi Zhang, Haoran Shen, Tianxiang Zhang
    AAAI 2024
    arXiv / Code / Project Page / BibTeX
    Service

  • Reviewer: NeurIPS 2024-2025, ICML 2025, ICLR 2025-2026, AAAI 2026, CVPR 2026

  • Website Template


    © Jing Wang | Last updated: December 23, 2025