CV

Changwang ZHANG is currently a senior researcher, he is a Standing Committee Member of CCF Theoretical Computer Science Technical Committee, and he is the Head of AI Agentic Information Retrieval Technology at the OPPO Research Institute. He received his MRes and PhD degrees from University College London in 2011 and 2015, respectively. He worked at Alibaba on LBS Data Mining from 2016 to 2017, and Tencent on Advertising Recommendation & User Profiling from 2018 to 2022.

Changwang ZHANG’s current interests are the research and application of AI Information Retrieval (Retrieval Augmented Generation, Multimodal Retrieval, Search-Recommendation-Advertising), AI agents (intention recognition, agent framework), and large AI models (large reasoning models R1/O1). He served as a Senior Program Committee (SPC) Member for the AAAI Conference on Artificial Intelligence.

Changwang Zhang’s research has got lots of media attention and is reported by the Guardian and the Daily Mail. He received the Tencent Gold Award for Excellence in R&D, the Tencent Operation Excellence Award, the Tencent Open Source Collaboration Award, and the Tencent Micro Innovation Award. For Tencent and Alibaba, he interviewed more than 300 candidates from fresh graduates to experienced hires. And He was the official technical interviewer & speaker for the offline on-site campus recruitment of Tencent.

Contacts: mleoking {at to remove} qq.com

Researchers Hiring and Funding Now: We are looking for outstanding highly motivated students and researchers to work together on the research and application of Information Retrieval (Recommendation & Search), Natural Language Processing, and Big Data Mining. Please email me with your CV and projects.

WeChat Official Account: Please follow the ‘‘旺知识’’ for more updated AI lectures, interviews, and R&D experience in Chinese.

Representative Work

• We have developed OEmbedding, a Vision-Language Model (VLM)-native representational foundation model. By proposing an innovative data curriculum and attention enhancement mechanism, we have significantly improved multimodal representation performance. OEmbedding-v1-7B has ranked 4th on the MMEB-v1 international image-text representation benchmark (Data as of 20250911).
• We propose the OThink-MR1 (paper) multimodal reasoning model and framework, and this technology enables the industry to break through the generalization and reasoning capabilities in multimodal tasks. We proposed the GRPO-D dynamic reinforcement learning algorithm. GRPO-D has demonstrated excellent cross-task generalization ability in multimodal task evaluation. Compared with supervised fine-tuning (SFT), it has achieved an average relative performance improvement of more than 61.63%.
• We propose the EulerFormer model (SIGIR’24, paper) that significantly improves the expressive power and robustness of the Transformer model through the complex attention network and adaptive rotational position coding. EulerFormer provided a unified theoretical framework to formulate both semantic and positional information, thus possessing a stronger expressive capacity in sequential modeling. Specially, in EulerFormer, both semantic difference and positional difference among tokens can be directly modeled in a unified rotation form of complex vector. Compared with prior methods (e.g., RoPE), EulerFormer is more robust to semantic variations and have more superior theoretical properties (e.g., long-term decay).
• We present PoseCrafter (ECCV’24, paper), a novel approach for personalized video generation with precise control over flexible poses. Leveraging the Stable Diffusion and ControlNet frameworks, we meticulously devise an inference process to yield top-tier videos without relying on corresponding ground-truth frames. We employ straightforward latent editing through an affine transformation matrix encompassing facial and hand landmarks. Comprehensive experiments across multiple datasets demonstrate that PoseCrafter outperforms baselines pre-trained on an extensive array of videos across 8 widely used metrics. Additionally, PoseCrafter is capable of adhering to poses from various individuals or artificial edits while preserving human identity in open-domain training videos simultaneously.
• Changwang Zhang proposes the PromptAppGPT - a low-code prompt-based rapid app development framework, aiming to enable natural language app development based on GPT. PromptAppGPT significantly lowers the barrier to GPT application development, allowing anyone to develop AutoGPT-like applications with a few lines of low code. And PromptAppGPT has been featured in many high-impact media including the top Chinese AI media: 新智元1, 新智元2. You are wellcome to: 1. Join us to collaboratively develop the framework: https://github.com/mleoking/PromptAppGPT/; 2. Visit the website to try the framework: https://promptappgpt.wangzhishi.net/; 3. See the example apps including the 70-line low-code implementation of the AutoGPT-like AI auto-assistant: https://github.com/mleoking/PromptAppGPT/blob/main/PagApps.md#my-autogpt.

Education

• MRes in Multidisciplinary (inc. Computer Science) with Distinction, University College London, 2011
• PhD in Multidisciplinary (inc. Computer Science), University College London, 2015

Work Experience

• 2018.01 - : Senior Researcher at the Tencent Holdings Ltd
  • Advertising Recommendation & User Profiling
• 2016.06-2017.12: Algorithm Expert at the Alibaba Group
  • Location Based Service (LBS) Data Mining and Applications

Services

• Member of the CCF Theoretical Computer Science Technical Committee
• Senior Program Committee (SPC) Member for the 37th AAAI Conference on Artificial Intelligence (AAAI-23)
• Senior Program Committee (SPC) Member for the 38th AAAI Conference on Artificial Intelligence (AAAI-24)
• Official technical interviewer & speaker for the offline on-site campus recruitment of Tencent
• Supervisor for students in Information Retrieval for the Tencent’s Rhino-Bird Elite Talent Program

Selected Publications

• B Wang, F Liu, J Chen, X Lou, C Zhang, J Wang, Y Sun, Y Feng, C Chen, C Wang. MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender. ACM SIGIR Conference on Research and Development in Information Retrieval, 2025. (SIGIR 2025) (CCF A) (pdf code)
• B Gan, Y Zhao, T Zhang, J Huang, Y Li, S X Teo, C Zhang, W Shi. MASTER: A Multi-Agent System with LLM Specialized MCTS. North American Chapter of the Association for Computational Linguistics, 2025. (NAACL 2025) (CCF B) (pdf code)
• R Feng, Z Tian, Q Peng, J Mao, X Zhao, D Hu, C Zhang. MGIPF: Multi-Granularity Interest Prediction Framework for Personalized Recommendation. ACM SIGIR Conference on Research and Development in Information Retrieval, 2025. (SIGIR 2025) (CCF A) (pdf code)
• H Huang, X Lou, C Zhang, C Chen, K Dong, F Lu, H Lei, Y Wang, W Zhou, J Wang. Training-free Periodic Interest Augmentation in Incremental Recommendation. ACM SIGIR Conference on Research and Development in Information Retrieval, 2025. (SIGIR 2025) (CCF A) (pdf code)
• Z Tian, W Zhao, C Zhang, X Zhao, Z Ma, J Wen. EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention. ACM SIGIR Conference on Research and Development in Information Retrieval, 2024. (SIGIR 2024) (CCF A) (pdf code)
• Y Zhong, M Zhao, Z You, X Yu, C Zhang, C Li. PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control, 2024. (ECCV 2024) (CCF B) (pdf code)
• Y Ye, Z Li, Z Dou, Y Zhu, C Zhang, S Wu, Z Cao. Learning from the Wisdom of Crowds: Exploiting Similar Sessions for Session Search. Proceedings of the AAAI Conference on Artificial Intelligence, 2023. (AAAI 2023) (CCF A) (pdf code)
• P Zhang, S Wang, L Li, C Zhang, X Liu, E Zhu, Z Liu, L Zhou, L Luo. Let the Data Choose: Flexible and Diverse Anchor Graph Fusion for Scalable Multi-View Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 2023. (AAAI 2023) (CCF A) (pdf code)
• Z Zheng, C Zhang, X Gao, G Chen. HIEN: Hierarchical Intention Embedding Network for Click-Through Rate Prediction. ACM SIGIR Conference on Research and Development in Information Retrieval, 2022. (SIGIR 2022) (CCF A) (pdf code)
• W Tu, S Zhou, X Liu, Y Liu, Z Cai, E Zhu, C Zhang, J Cheng. Initializing Then Refining: A Simple Graph Attribute Imputation Network. International Joint Conference on Artificial Intelligence (IJCAI), 2022. (IJCAI 2022) (CCF A) (pdf code)
• S Liu, S Wang, P Zhang, K Xu, X Liu, C Zhang, F Gao. Efficient one-pass multi-view subspace clustering with consensus anchors. Proceedings of the AAAI Conference on Artificial Intelligence, 2022. (AAAI 2022) (CCF A) (pdf code)
• Y Zhang, X Liu, J Liu, S Dai, C Zhang, K Xu, E Zhu. Fusion Multiple Kernel K-means. Proceedings of the AAAI Conference on Artificial Intelligence, 2022. (AAAI 2022) (CCF A) (pdf code)
• C Zhang, S Wang, J Liu, S Zhou, P Zhang, X Liu, E Zhu, C Zhang. Multi-view Clustering via Deep Matrix Factorization and Partition Alignment. ACM International Conference on Multimedia, 2021. (ACMMM 2021) (CCF A) (pdf code)
• S Zhou, X Liu, M Li, E Zhu, L Liu, C Zhang, J Yin. Multiple kernel clustering with neighbor-kernel subspace segmentation. IEEE transactions on neural networks and learning systems, 2019. (TNNLS 2019) (CCF B) (pdf code)
• C Zhang, S Zhou, E Groppelli, P Pellegrino, I Williams, P Borrow, B M. Chain, C Jolly. Hybrid Spreading Mechanisms and T Cell Activation Shape the Dynamics of HIV-1 Infection. PLOS Computational Biology, 2015. (PLoS Comput. Biol. 2015) (CCF B) (pdf code)

Selected Media Coverage

• 业界突破多模态泛化推理能力，OPPO研究院&港科广提出OThink-MR1技术, 量子位, 2025.
• 真低代码！首个基于ChatGPT的自然语言开发框架PromptAppGPT：全自动编译、运行、界面生成, 新智元, 2023.
• PromptAppGPT重磅更新！AI助手0门槛开发+运行：几十行代码即可实现AutoGPT, 新智元, 2023.
• ​2023年人工智能体(AI Agent)开发与应用全面调研：概念、原理、开发、应用、挑战、展望, 旺知识, 2024.
• AFSPP唤醒智能体内心世界：首个支持心理学实验的AI Agent偏好性格塑造框架发布!, 旺知识, 2024.
• 高级检索增强生成技术(RAG)全面指南：原理、分块、编码、索引、微调、Agent、展望, 旺知识, 2024.
• HIV spreads like computer worms, say scientists, The Guardian, 2015.
• HIV spreads like a computer worm: Researchers find virus mimics an online infection - and warn early detection is key, Daily Mail, 2015.

Selected Talks

• C Zhang. Panel Talk: Big-data Mining Using Unsupervised Learning and Graph Learning. IJCAI-Tencent Academic and Industrial Conference, 2019. (pdf poster)
• C Zhang. Tencent Campus Recruitment Talk - Beijing University of Posts and Telecommunications. Beijing University of Posts and Telecommunications, 2020. (pdf poster)
• C Zhang. Tencent Campus Recruitment Talk - Huazhong University of Science and Technology. Huazhong University of Science and Technology, 2021. (pdf poster)
• C Zhang. Tencent Campus Recruitment Talk - Universities in the Western US Region. Universities in the Western US Region, 2021. (pdf poster)