Education

• Peking University, Data Science (Computer Science and Technology), Master degree, 2018-2021
• Wuhan University, Computer Science and Technology, Bachelor degree, 2014-2018
  • GPA: 3.83, Ranking: 1/38, CET-6: 571

Work Experience

• AIGC Technical Leader, Commercialization Algorithm Department, Kuaishou. (2025.01 - Present)

  • Leading AdsLLM and AI Agents for Kuaishou’s commercialization business, including zero-material ad generation, intelligent customer service, and ad delivery agents.
  • Built an AIGC advertising agent that automatically generates short video ads from product images or landing pages at large scale and very low cost.
  • Led the AI novel agent system and generative recommendation research for large-scale monetization scenarios, and drove research on controllable video generation and multimodal ad editing.

• Senior AIGC Algorithm Engineer, Commercialization GenAI, ByteDance. (2023.03 - 2025.01)

  • Led AdsLLM for commercialization, including continued pretraining, alignment, evaluation, and platformization for multiple advertising applications.
  • Built high-quality pretraining and SFT data pipelines, improved long-context and agent-related abilities, and established a comprehensive evaluation framework.

• Computer Vision Algorithm Engineer, AI-Lab, ByteDance. (2021.10 - 2023.03)

  • Led the video-to-product retrieval project and supported large-scale e-commerce and advertising scenarios with multimodal understanding and retrieval.
  • Built capabilities including intent recognition, detection and tracking, multimodal representation, ANN retrieval, and ranking.

• Computer Vision Algorithm Engineer, AI-Lab, ByteDance. (2021.06 - 2021.10)

  • Built multimodal ad understanding models to improve CTR and CVR prediction by combining video and text information.

• Algorithm Engineer Intern, Alibaba Group. (2020.07 - 2020.10)

  • Worked on advertising creative material mining, object matting, image generation, and video understanding.

• Research Intern, Medical AI Lab, Tencent. (2018.07 - 2019.07)

  • Responsible for the research and development of the core module in the intelligent medical qualification examination system. The final model can score more than 390 points in the national medical qualification examination, which outperformed more than 70% of the human examinees.
  • Researched the automatic generation of medical diagnostic reports for chest X-rays.

• Engineering Intern, Tencent Cloud. (2017.07 - 2017.09)
  • Responsible for the Panshi system decoupling and reconstruction. Separated the system’s web access layer from its data access layer; completed the modification of related data interfaces.
  • Developed and maintained the related functional plugins of the system.

• Exchange Student in Hong Kong Baptist University. (2017.05 - 2017.06)
  • Researched on blockchain technology.

Publications

Google Scholar: 412 citations, h-index 7, i10-index 7.

Preprint / Under Review

1. Z. Xie, Yuyang You, Yongzhi Li, E. Gong, Z. Chen, Quan Chen, Y. Cheng, Peng Jiang, Yadong Mu, “ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy”, arXiv:2607.03126, 2026. [arXiv] [pdf]

2. Y. Cheng, B. Wang, H. Zhang, X. Gao, Z. Yin, Ben Xue, Yongzhi Li, J. Xue, Y. Ma, et al., “Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale”, arXiv:2606.25496, 2026. [arXiv] [pdf]

3. X. Zhang, Yongzhi Li, L. Xiao, Y. Zhang, Y. Cheng, Quan Chen, Peng Jiang, W. Wu, L. Liu, “FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning”, arXiv:2605.20256, 2026. [arXiv] [pdf]

4. Ben Xue, J. Wang, Yongzhi Li, J. Lan, H. Xu, J. Jia, Peng Jiang, Quan Chen, Kun Gai, L. Liu, et al., “Universal Discrete Tokenizers: Principles, Applications, and Future Directions”, TechRxiv preprint, 2026. [pdf]

5. X. Zhang, B. Wang, L. Xiao, Yongzhi Li, Quan Chen, W. Wu, L. Liu, “Imagine: Integrating Multi-Agent System into One Model for Complex Reasoning and Planning”, arXiv:2510.14406, 2025. [arXiv] [pdf]

Conference Paper

1. Yuyang You, Yongzhi Li^†, Jiahui Li, Yadong Mu, Quan Chen, Peng Jiang, “Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2026. [pdf]

2. Zhengjian Yao, Yongzhi Li^†, Xinyuan Gao, Quan Chen, Peng Jiang, Yanye Lu, “Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2026. [pdf]

3. Milton Zhou^*, Sizhong Qin^*, Yongzhi Li^†, Quan Chen, Peng Jiang, “AutoCut: End-to-end Advertisement Video Editing Based on Multimodal Discretization and Controllable Generation”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2026. [pdf]

4. Ben Xue, Dan Liu, et al., Yongzhi Li, Quan Chen, Peng Jiang, Kun Gai, “Generative Recommendation for Large-Scale Advertising”, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2026. [pdf]

5. Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong MU, “Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023. [pdf]

6. Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong MU, “Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding”, NeurIPS 2022[pdf]

7. Liangfeng Zheng, Yongzhi Li, Yadong Mu, “Learning Factorized Cross-View Fusion for Multi-View Crowd Counting”, IEEE International Conference on Multimedia and Expo (ICME) 2021.[pdf] [bibtex]

8. Yongzhi Li, Yadong Mu, Nan Zhuang, Xianglong Liu, “Efficient Fine-Grained Visual-Text Search Using Adversarially-Learned Hash Codes”, IEEE International Conference on Multimedia and Expo (ICME) 2021. [pdf] [bibtex]

9. Chenchen Liu, Yongzhi Li, Kangqi Ma, Duo Zhang, Peijun Bao, Yadong Mu,
   “Learning 3-D Human Pose Estimation from Catadioptric Videos”, The 30th International Joint Conference on Artificial Intelligence (IJCAI) 2021.[pdf] [bibtex]

10. Yongzhi Li, Duo Zhang, Yadong Mu, “Visual-Semantic Matching by Exploring High-Order Attention and Distraction”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020. [pdf] [Bibtext]

11. Yongzhi Li, Lu Chi, Guiyu Tian, Yadong Mu, Shen Ge, Zhi Qiao, Xian Wu, Wei Fan, “Spectrally-Enforced Global Receptive Field for Contextual Medical Image Segmentation and Classification”, IEEE International Conference on Multimedia and Expo (ICME) 2020. [pdf] [Bibtext]

12. Xinyu Weng^†, Yongzhi Li^†, Lu Chi, Yadong Mu, “High-Capacity Convolutional Video Steganography with Temporal Residual Modeling”, ACM International Conference on Multimedia Retrieval (ICMR) 2019. (Oral Presentation) [pdf] [Bibtext]

Projects

Most projects and introductions are shown in the project page

Academic Service

• Reviewer of CVPR 2023
• Reviewer of Neural Computing

Skills

• Familiar with Python, C++, and Golang
• Proficient in PyTorch and Transformers, with experience in computer vision, multimodal learning, LLMs, and AIGC systems.