About Me

I’m a Senior Researcher at Microsoft Research. I received my Bachelor’s degree and Ph.D. from Tsinghua University in 2016 and 2021, respectively. My recent research focuses on multimodal modeling and AI Agents.

📢 I’m looking for a self-motivated research intern who is passionate about AI agents. If you are interested in this topic, feel free to email me your resume and a brief self-intro!

News

• [ 06/03/2025 ] Excited to release our GUI-Actor, a coordinate-free visual grounding method for GUI agents!
• [ 04/28/2025 ] You’re welcome to join our 4th Workshop on Computer Vision in the Wild (CVinW) at @CVPR 2025!
• [ 02/26/2025 ] Magma is accepted by CVPR 2025!
• [ 02/18/2025 ] We release Magma, a foundation model for multimodal AI agents!
• [ 01/22/2025 ] SeCom and SCBench are accepted at ICLR 2025!
• [ 09/25/2024 ] MInference is accepted at NeurIPS 2024 as a spotlight!
• [ 05/21/2024 ] LLMLingua Series has been integrated as a custom tool in Prompt Flow, AutoGen, LangChain and LlamaIndex.

Recommended Repos

• GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
• Magma: A Foundation Model for Multimodal AI Agents
• MInference: Million-Tokens Prompt Inference for Long-context LLMs
• LLMLingua Series for Prompt Compression
• Versatile Entity Recognition & disambiguation Toolkit

Selected Publications

• Qianhui Wu* , Kanzhi Cheng* , Rui Yang*, Chaoyun Zhang, Jianwei Yang, Huiqiang Jiang, Jian Mu, Baolin Peng, Bo Qiao, Reuben Tan, Si Qin, Lars Liden, Qingwei Lin, Huan Zhang, Tong Zhang, Jianbing Zhang, Dongmei Zhang, Jianfeng Gao, GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents, preprint.
• Jianwei Yang* , Reuben Tan* , Qianhui Wu*, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang, Yuquan Deng, Jianfeng Gao, Magma: A Foundation Model for Multimodal AI Agents, CVPR-2025.
• Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Xufang Luo, Hao Cheng, Dongsheng Li, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Jianfeng Gao, Secom: On Memory Construction and Retrieval for Personalized Conversational Agents, ICLR-2025, AFM@NeurIPS-2024.
• Yucheng Li, Huiqiang Jiang, Qianhui Wu, Xufang Luo, Surin Ahn, Chengruidong Zhang, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu, SharedContextBench: How Lossy are Long-context Methods in KV Cache Reuse, ICLR-2025.
• Huiqiang Jiang* , Yucheng Li* , Chengruidong Zhang*, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir H. Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu, MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention, NeurIPS-2024 spotlight.
• Zhoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Dongmei Zhang, LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression, ACL-2024 Findings.
• Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongshegn Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu, LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression, ACL-2024, ME-FoMo@ICLR-2024.
• Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, Lili Qiu, LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models, EMNLP-2023.
• Qianhui Wu, Huiqiang Jiang, Haonan Yin, Börje Karlsson, Chin-Yew Lin, Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text, ACL-2023.

Honors & Awards

• Microsoft 2024 Global Hackathon Executive Challenge Winner (2024)
• Microsoft Machine Learning, AI & Data Science Conference (MLADS) Distinguished Contribution Award Winner (2024)
• Microsoft 2023 Global Hackathon Award Winner (2023)
• Intel Scholarship (2020)
• Outstanding (12-9) Counselor Prize, Tsinghua University (2018)
• Outstanding Bachelor Thesis, Tsinghua University (2016)
• National Encouragement Scholarship (2014)
• Scholarship of Art Excellence, Tsinghua University (2014)
• Scholarship of Academic Excellence, Tsinghua University (2013)

Other Information

Invited Talks

• [ 09/05/2025 ] Towards AI Agents That Can See And Act @ Shanghai Artificial Intelligence Laboratory
• [ 06/25/2025 ] Act Where You See: Coordinate-Free Visual Grounding for GUI Agents @ Simular Seminar

Academic Service

• Area Chair: COLING-25.
• Conference Reviewer: ICLR, NeurIPS, ACL, EMNLP, NAACL, AAAI, NLPCC.
• Journal Reviewer: CSUR, TOIS, Pattern Recognition, TASLP, IPM, JIM, ESIN, SIVP.

Other Activities

• Counselor at Center for Student Learning and Development, Tsinghua University (Sep. 2016 - Aug. 2018)
• Member of Chinese National Orchestra, Tsinghua University (Aug. 2012 - Jun. 2021)