Yan Li (李岩)

Tech Lead Manager, Content AI

TikTok, Core Recommendation.

Biography

I am currently a Tech Lead Manager at TikTok, leading the Content AI team within the Core Recommendation department.

My team focuses on empowering recommendation businesses with advanced content understanding capabilities. My current research interests include Multimodal Large Language Models (MLLMs), universal video representations, and next-generation recommendation systems powered by Generative AI.

Before that, I received my PhD degree in Pattern Recognition and Intelligent System from Institute of Automation, Chinese Academy of Sciences (CASIA) in 2019 advised by Kaiqi Huang and my bachelor degree in Automation from Department of Automation, Tsinghua University in 2014.

Interests

Multimodal Large Language Models
Recommendation Systems
Computer Vision
Artificial Intelligence

Education

PhD in Pattern Recognition and Intelligent System, 2014-2019
Institution of Automation, Chinese Academy of Sciences (CASIA)
BSc in Automation, 2010-2014
Department of Automation, Tsinghua University

Professional Experience

Ph.D. Graduation
2019.05 | Zero/Few-shot learning
Tencent, PCG Group | Computer Vision Researcher
2019.08 – 2021.03
Video action understanding
Kuaishou, Advertising Algorithm Department | Senior Algorithm Researcher
2021.03 – 2024.03
Ads/e-commerce understanding; LLM for recommendation
TikTok, Content AI, Core Recommendation | Tech Lead Manager
2024.04 – Present
Multimodal LLM & video representation; Supporting core & next-gen RecSys

Publications

[AAAI2024] “LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application.” Jian Jia, Yipei Wang, Yan Li, Honggang Chen, Xuehan Bai, Zhaocheng Liu, Jian Liang, Quan Chen, Han Li, Peng Jiang, Kun Gai.
[ICCV2023] “Cross-Domain Product Representation Learning for Rich-Content E-Commerce.” Xuehan Bai, Yan Li (co-first author), Yanhua Cheng, Wenjie Yang, Quan Chen, Han Li. [arxiv] [code]
[ICCV2023] “Cross-view Semantic Alignment for Livestreaming Product Recognition.” Wenjie Yang, Yiyi Chen (co-first author), Yan Li, Yanhua Cheng, Xudong Liu, Quan Chen, Han Li. [arxiv] [code]
[CVPR2020] “TEA: Temporal Excitation and Aggregration for Action Recognition.” Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, Limin Wang. [arxiv_with_suppl] [paper] [code]
[NeurIPS19] “Transductive Zero-Shot Learning with Visual Structure Constraint.” Ziyu Wan, Dongdong Chen, Yan Li, Junge Zhang, Yizhou Yu and Jing Liao. [arxiv]
[ICCV19] “Few-Shot Image Recognition with Knowledge Transfer.” Zhimao Peng, Zechao Li, Junge Zhang, Yan Li, Guo-Jun Qi, Jinhui Tang.
[TPAMI19] “Mixed Supervised Object Detection with Robust Objectness Transfer.” Yan Li, Junge Zhang, Kaiqi Huang, Jianguo Zhang. [arxiv with suppl] [paper]
[CVPR18 (Oral)] “Discriminative Learning of Latent Features for Zero-Shot Recognition.” Yan Li, Junge Zhang, Jianguo Zhang, Kaiqi Huang. [arxiv with suppl] [paper]
[AAAI18] “Deep Semantic Structural Constraints for Zero-Shot Learning.” Yan Li, Zhen Jia (co-first author), Junge Zhang, Kaiqi Huang, Tieniu Tan. [paper]