Junwei Pan

Junwei Pan

I'm a Research Scientist at Tencent, working on recommendation systems and computational advertising. Before that, I was a Principal Research Engineer at Yahoo! Labs/Research, working on streaming news recommendations, relevance search, and online advertising. I received my M.S. degree from Renmin University of China, advised by Prof. Jiaheng Lu.

jonaspan [AT] tencent.com, pandevirus [AT] gmail.com
[Google Scholar] [Semantic Scholar] [ResearchGate]
Binhai Building, Tencent, Shenzhen, China

Tutorial

  1. Computational Advertising: Recent Advances [slides]
    Junwei Pan, Zhilin Zhang, Han Zhu, Jian Xu, Jie Jiang, Bo Zheng
    WWW, May 2025.

Talk

  1. Large-scale Generative and Multimodal Recommendation Systems: An Overview [slides]
    International Workshop on Multimodal Generative Search and Recommendation [link]
    CIKM, Nov 2025.

Preprint

(* Equal Contribution)

  1. Large Foundation Model for Ads Recommendation [arXiv]
    Shangyu Zhang, Shijie Quan, Zhongren Wang, Junwei Pan, Tianqu Zhuang, et. al.

  2. Practice on Long Behavior Sequence Modeling in Tencent Advertising [arXiv]
    Xian Hu, Ming Yue, Zhixiang Feng, Junwei Pan, Junjie Zhai,, et. al.

  3. Generative Multi-Target Cross-Domain Recommendation [arXiv]
    Jinqiu Jin, Yang Zhang, Junwei Pan, Fuli Feng, Hua Lu, Haijie Gu, Xiangnan He

  4. Enhancing CTR Prediction with De-correlated Expert Networks [arXiv]
    Jiancheng Wang, Mingjia Yin, Junwei Pan, Ximei Wang, Hao Wang and Enhong Chen

  5. Towards Scalable Semantic Representation for Recommendation [arXiv]
    Taolin Zhang, Junwei Pan, Jinpeng Wang, Yaohua Zha, Tao Dai, Bin Chen, Ruisheng Luo, XiaoxiangDeng, Yuan Wang, Ming Yue, Jie Jiang, Shu-Tao Xia

Publications

(* Equal Contribution)

  1. Cross-Scale Model Collaboration for Sequential Recommendation with Domain-Specific Latent Reasoning
    Yipeng Zhang, Xin Wang, Hong Chen, Junwei Pan, Qian Li, Jun Zhang, Jie Jiang, Hong Mei, Wenwu Zhu
    AAAI Conference on Artificial Intelligence (AAAI), 2026

  2. Incremental Learning for LLM-based Tokenization and Recommendation
    Haihan Shi, Xinyu Lin, Wenjie Wang, Wentao Shi, Junwei Pan, Jie Jiang and Fuli Feng
    The Conference on Information and Knowledge Management (CIKM) , 2025

  3. Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs
    Yuhao Wang, Junwei Pan, Xinhang Li, Maolin Wang, Yuan Wang, Yue Liu, Dapeng Liu, Jie Jiang and Xiangyu Zhao
    The Conference on Information and Knowledge Management (CIKM) , 2025

  4. Crocodile: Cross Experts Covariance for Disentangled Learning in Multi-Domain Recommendation [arXiv]
    Zhutian Lin, Junwei Pan, Haibin Yu, Xi Xiao, Ximei Wang, Zhixiang Feng, Shifeng Wen, Shudong Huang, Lei Xiao, Jie Jiang
    The Conference on Information and Knowledge Management (CIKM) , 2025 \[\mathcal{L}_{Cov}= \frac{1}{d^2}\sum\limits_{p, q \in M\times M, p>q}||[\mathbf{O}^{(p)}-\overline{\mathbf{O}}^{(p)}]^T[\mathbf{O}^{(q)}-\overline{\mathbf{O}}^{(q)}]||_1\]

  5. Towards Unifying Feature Interaction Models for Click-Through Rate Prediction [arXiv]
    Yu Kang, Junwei Pan, Jipeng Jin, Shudong Huang, Xiaofeng Gao, Lei Xiao
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) , 2025

  6. From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
    Mingjia Yin, Junwei Pan, Hao Wang, Ximei Wang, Shangyu Zhang, Jie Jiang, Defu Lian, Enhong Chen
    International Conference on Machine Learning (ICML) , 2025 \[f_\text{decoder}^j(\{\mathbf{v}_i\}_\text{source}) \odot f_\text{transform}\{{\mathbf{v}_i\}_\text{target}}\]

  7. Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models
    Yuhao Wang, Junwei Pan, Xiangyu Zhao, Pengyue Jia, Wanyu Wang, Yuan Wang, Yue Liu, Dapeng Liu, Jie Jiang
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) , 2025 [arXiv]

  8. Long-Sequence Recommendation Models Need Decoupled Embeddings [arXiv]
    Ningya Feng*, Junwei Pan*, Jialong Wu*, Baixu Chen, Ximei Wang, QianLi, Xian Hu, Jie Jiang, Mingsheng Long International Conference on Learning Representations (ICLR) , 2025 \[\textbf{h} = \sum_{i=1}^{K} \frac{e^{\langle \textbf{e}_i^\text{Att}, \textbf{v}_t^\text{Att} \rangle}}{\sum_{j=1}^{K}e^{\langle \textbf{e}_j^\text{Att}, \textbf{v}_t^\text{Att} \rangle}} \cdot (\textbf{e}_i^\text{Repr} \odot \textbf{v}_t^\text{Repr}).\]

  9. Ads Recommendation in a Collapsed and Entangled World [arXiv] [slides] [code] [poster]
    Junwei Pan, Wei Xue, Ximei Wang, Haibin Yu, Xun Liu, Shijie Quan, Xueming Qiu, Dapeng Liu, Lei Xiao, Jie Jiang
    ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD) , 2024

  10. Understanding the Ranking Loss for Recommendation with Sparse User Feedback [arXiv] [slides] [code] [poster]
    Zhutian Lin*, Junwei Pan*, Shangyu Zhang, Ximei Wang, Xi Xiao, Shudong Huang, Lei Xiao, Jie Jiang
    ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD) , 2024 \[\nabla_{z_j^{(-)}} \mathcal{L}_\text{Rank} = \frac{1}{N_+} \sum_{i=1}^{N_+} \sigma(z_j^{(-)}-z_i^{(+)}) > \frac{1}{N_+}\cdot N_+\cdot \sigma(z_j^{(-)}) = \sigma(z_j^{(-)}) = \nabla_{z_j^{(-)}} \mathcal{L}_\text{BCE}\]

  11. On the Embedding Collapse when Scaling up Recommendation Models [arXiv] [slides] [code] [poster]
    Xingzhuo Guo, Junwei Pan, Ximei Wang, Baixu Chen, Jie Jiang, Mingsheng Long
    International Conference on Machine Learning (ICML) , 2024 \[\textbf{e}_i =\textbf{E}_i^{\top}\textbf{1}_{x_i},\ \forall i\in\{1,2,...,N\}; h=I(\textbf{e}_1,\textbf{e}_2,...,\textbf{e}_n); \hat{y}=F(h)\]

  12. Deep Pattern Network for Click-Through Rate Prediction [arXiv]
    Hengyu Zhang, Junwei Pan, Dapeng Liu, Jie Jiang and Xiu Li
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) , 2024

  13. Temporal Interest Network for User Response Prediction [arXiv] (Oral) [slides] [code] [poster]
    Haolin Zhou*, Junwei Pan*, Xinyi Zhou, Xihua Chen, Jie Jiang, Xiaofeng Gao, Guihai Chen
    World Wide Web Conference (WWW), 2024 \[\textbf{u} = \sum_{i \in \mathcal{H}} \alpha(\tilde{\textbf{e}}_{i}, \tilde{\textbf{v}}_{t}) \cdot (\tilde{\textbf{e}}_{i} \odot \tilde{\textbf{v}}_t)\]

  14. Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning
    Ximei Wang, Junwei Pan, Xingzhuo Guo, Dapeng Liu, Jie Jiang
    AAAI Conference on Artificial Intelligence (AAAI), 2024 [arXiv] [poster]

  15. STEM: Unleashing the Power of Embeddings for Multi-task Recommendation
    Liangcai Su*, Junwei Pan*, Ximei Wang, Xi Xiao, Shijie Quan, Xihua Chen, Jie Jiang
    AAAI Conference on Artificial Intelligence (AAAI), 2024 [arXiv] [code] [poster] \[\textbf{o}^{t} = \sum_{i}^{K_2} \textbf{g}^{S\rightarrow{t}}_{i} \textbf{h}^{S}_{i}(\textbf{E}^S) + \sum_{i}^{K_1} \textbf{g}^{t\rightarrow{t}}_{i} \textbf{h}^{t}_{i}(\textbf{E}^t) + \sum_{t' \in {\mathcal{T}}, t'\neq{t}}\sum_{i}^{K_1} \textbf{g}^{t'\rightarrow{t}}_{i}\texttt{SG}(\textbf{h}^{t'}_i(\textbf{E}^{t'}))\]

  16. Multi-Sequence Attentive User Representation Learning for Side-information Integrated Sequential Recommendation [PDF]
    Xiaolin Lin, Jinwei Luo, Junwei Pan, Weike Pan, Zhong Ming, Xun Liu, Shudong Huang, Jie Jiang
    ACM International Conference on Web Search and Data Mining (WSDM), 2024

  17. AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning [PDF] (Oral)
    Enneng Yang*, Junwei Pan*, Ximei Wang, Haibin Yu, Li Shen, Xihua Chen, Lei Xiao, Jie Jiang, Guibing Guo
    AAAI Conference on Artificial Intelligence (AAAI), 2023 \[\theta_{t+1,i} = \theta_{t,i} - \sum_k \frac{\eta}{\sqrt{ {G}_{t,i}^k} + \epsilon} {g}_{t,i}^k, G_{t,i}^k = G_{t-1,i}^k \!+\! {(g_{t,i}^k)}^2 \]

  18. ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning [arXiv]
    Junguang Jiang, Baixu Chen, Junwei Pan, Ximei Wang, Liu Dapeng, Jie Jiang, Mingsheng Long
    Neural Information Processing Systems (NeurIPS), 2023

  19. AutoAttention: Automatic Field Pair Selection for Attention in User Behavior Modeling [arXiv]
    Zuowu Zheng, Xiaofeng Gao, Junwei Pan, Qi Luo, Guihai Chen, Dapeng Liu, Jie Jiang
    IEEE International Conference on Data Mining (ICDM), 2022 \[a(\textbf{v}_i, \textbf{e}_{F_{1:M}}) = \sigma\left(b + \sum_{p=1}^P \sum_{j=1}^M \langle \textbf{v}_{B_p}, \textbf{e}_{F_j} \rangle r_{B_p,F_j}\right)\]

  20. Cross-task Knowledge Distillation in Multi-task Recommendation [arXiv]
    Chenxiao Yang, Junwei Pan, Xiaofeng Gao, Tingyu Jiang, Dapeng Liu, Guihai Chen
    AAAI Conference on Artificial Intelligence (AAAI), 2022

  21. Trading Hard Negatives and True Negatives: A Debiased Contrastive Collaborative Filtering Approach [arXiv]
    Chenxiao Yang, Qitian Wu, Jipeng Jin, Xiaofeng Gao, Junwei Pan, Guihai Chen
    International Joint Conference on Artificial Intelligence (IJCAI), 2022

  22. Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback [PDF]
    Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR, short) , 2021

  23. Impression Allocation and Policy Search in Display Advertising [arXiv]
    Di Wu, Cheng Chen, Xiujun Chen, Junwei Pan, Xun Yang, Qing Tan, Jian Xu, Kuang-Chih Lee
    IEEE International Conference on Data Mining (ICDM) , 2021

  24. A Unified Solution to Constrained Bidding in Online Display Advertising [PDF]
    Yue He, Xiujun Chen, Di Wu, Junwei Pan, Qing Tan, Chuan Yu, Jian Xu, Xiaoqiang Zhu
    ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD) , 2021

  25. DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving [arXiv]
    Wei Deng*, Junwei Pan*, Tian Zhou, Deguang Kong, Aaron Flores, Guang Lin
    ACM International Conference on Web Search and Data Mining (WSDM) , 2021

  26. FM^2: Field-matrixed Factorization Machines for CTR Prediction [arXiv]
    Yang Sun, Junwei Pan, Alex Zhang, Aaron Flores
    World Wide Web Conference (WWW) , 2021 \[ \sum_i \sum_j x_i x_j \langle \textbf{v}_i M_{F(i), F(j)}, \textbf{v}_j \rangle \]

  27. Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising [PDF]
    Zhilin Zhang, Xiangyu Liu, Zhenzhe Zheng, Chenrui Zhang, Miao Xu, Junwei Pan, Chuan Yu, Fan Wu, Jian Xu, Kun Gai
    ACM International Conference on Web Search and Data Mining (WSDM), 2021

  28. An Efficient Deep Distribution Network for Bid Shading in First-price Auctions [PDF]
    Tian Zhou, Hao He, Shengjun Pan, Niklas Karlsson, Bharatbhushan Shetty, Brendan Kitts, Djordje Gligorijevic, San Gultekin, Tingyu Mao, Junwei Pan, Jianlong Zhang, Aaron Flores
    ACM SIGKDD International Conference on Knowledge Discovery & Data mining (KDD), 2021

  29. Bid Shading by Win-Rate Estimation and Surplus Maximization [arXiv]
    Shengjun Pan, Brendan Kitts, Tian Zhou, Hao He, Bharatbhushan Shetty, Aaron Flores, Djordje Gligorijevic, Junwei Pan, Tingyu Mao, San Gultekin, Jianlong Zhang
    ACM SIGKDD International Conference on Knowledge Discovery & Data mining (AdKDD workshop in KDD), 2020

  30. Bid Shading in The Brave New World of First-Price Auctions [PDF]


    Djordje Gligorijevic, Tian Zhou, Bharatbhushan Shetty, Brendan Kitts, Shengjun Pan, Junwei Pan, Aaron Flores
    IEEE International Conference on Data Mining (ICDM), 2020

  31. Predicting Different Types of Conversions with Multi-task Learning in Online Advertising [PDF]
    Junwei Pan, Yizhi Mao, Alfonso Lobos Ruiz, Yu Sun, Aaron Flores
    ACM SIGKDD International Conference on Knowledge Discovery & Data mining (KDD), 2019 \[ \sum_i \sum_j x_i x_j \langle \textbf{v}_i, \textbf{v}_j \rangle r_{F(i), F(j)}^t \]

  32. A Batched Multi-armed Bandit Approach to News Headline Testing [arXiv]
    Yizhi Mao, Miao Chen, Abhinav Wagle, Junwei Pan, Michael Natkovich, Don Matheson
    IEEE International Conference on Big Data (Big Data ), 2018

  33. Field-weighted Factorization Machines for Click-through Rate Prediction in Display Advertising [PDF] (Oral) [slides]
    Junwei Pan, Jian Xu, Alfonso Lobos Ruiz, Wenliang Zhao, Shengjun Pan, Yu Sun, Quan Lu
    World Wide Web Conference (WWW), 2018 \[ \sum_i \sum_j x_i x_j \langle \textbf{v}_i, \textbf{v}_j \rangle r_{F(i), F(j)} \]

  34. A Practical Framework of Conversion Rate Prediction for Online Display Advertising [PDF]
    Quan Lu, Shengjun Pan, Liang Wang, Junwei Pan, Fengdan Wan, Hongxia Yang
    ACM SIGKDD International Conference on Knowledge Discovery & Data mining (AdKDD workshop in KDD) , 2017

Awards