Associate Professor / PhD Supervisor
Institute of Artificial Intelligence, Xiamen University
Jointly Appointed Associate Researcher, Peng Cheng Laboratory
IEEE Senior Member
I am an Associate Professor and PhD supervisor at the Institute of Artificial Intelligence, Xiamen University, a jointly appointed Associate Researcher at Peng Cheng Laboratory, and an IEEE Senior Member. I received my PhD from Xiamen University, advised by Prof. Rongrong Ji, and was a postdoctoral researcher at Peng Cheng Laboratory from 2022 to 2023, working with Prof. Yonghong Tian. My research focuses on automated machine learning, neural architecture search, model compression and efficient large-model deployment. I have published 25 CCF-A papers as first or corresponding author. My work has received over 13,000 citations on Google Scholar and has been cited multiple times in technical reports for Google's Gemini, Microsoft's Phi and Alibaba's Qwen. I lead an NSFC General Program project and multiple industry-sponsored projects with partners including Huawei, HiSilicon and ByteDance. The resulting technologies have been applied to products at Huawei, HiSilicon, Tencent, ByteDance, Alibaba/Tmall, HONOR, VIVO, OPPO and DiDi. I have received support from the Postdoctoral Innovative Talent Support Program, the China Postdoctoral Science Foundation and the Xiamen University Xiaomi Young Scholar Program, and collaborate on open-source research including MetaGPT with Jürgen Schmidhuber. I previously served on secondment in the Software Division of the Xiamen Municipal Bureau of Industry and Information Technology, contributing to AI innovation-center planning, industry development and policy materials. I teach Algorithm Design and Analysis and Art and Technology.
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models
Tianyu Xie, Jinfa Huang, Yuexiao Ma, Rongfang Luo, Yan Yang, Qingchuan Ma, Wang Chen, Yuhui Zeng, Yixuan Zou, Zhiqiang Lu, Ruize Fang, Jiebo Luo, Rongrong Ji, and Xiawu Zheng*
arXiv, 2026
Training-Free Multimodal Large Language Model Orchestration
Tianyu Xie, Yuexiao Ma, Yuhang Wu, Wang Chen, Jiayi Ji, Tat-Seng Chua, Xiawu Zheng*, and Rongrong Ji
ICML, 2026
A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
Qingchuan Ma, Yuexiao Ma, Yongkang Xie, Tianyu Xie, Xiawu Zheng*, and Rongrong Ji
ICML, 2026
QuoTA: Query-Oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
Yongdong Luo, Wang Chen, Weizhong Huang, Shukang Yin, Haojia Lin, Jinfa Huang, Chaoyou Fu, Jiayi Ji, Xiawu Zheng*, and Jiebo Luo
AAAI, 2026
Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
Wang Chen, Yuhui Zeng, Yongdong Luo, Tianyu Xie, Luojun Lin, Jiayi Ji, Yan Zhang, Xiawu Zheng*
CVPR, 2026
Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
Qingchuan Ma, Yuhang Wu, Xiawu Zheng*, and Rongrong Ji
ICML, 2025
Video-RAG: Visually-Aligned Retrieval-Augmented Long Video Comprehension
Yongdong Luo, Xiawu Zheng*, Guilin Li, Shukang Yin, Haojia Lin, Chaoyou Fu, Jinfa Huang, Jiayi Ji, Fei Chao, Jiebo Luo, and Rongrong Ji
NeurIPS, 2025
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
Chaoyou Fu, Haojia Lin, Xiong Wang, Yi-Fan Zhang, Yunhang Shen, Xiaoyu Liu, Haoyu Cao, Zuwei Long, Heting Gao, Ke Li, Long Ma, Xiawu Zheng, Rongrong Ji, Xing Sun, Caifeng Shan, and Ran He
NeurIPS, 2025
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-Modal LLMs in Video Analysis
Chaoyou Fu, Yuhan Dai, Yongdong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, Peixian Chen, Yanwei Li, Shaohui Lin, Sirui Zhao, Ke Li, Tong Xu, Xiawu Zheng, et al.
CVPR, 2025
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, Rongrong Ji, Caifeng Shan, and Ran He
NeurIPS Datasets and Benchmarks Track, 2025
MetaGPT: Meta Programming for Multi-Agent Collaborative Framework
Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven K. S. Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber
ICLR, 2024
Good Performance Estimation Strategies Are All You Need in Neural Architecture Search
Xiawu Zheng, Lei Zhang, Binghan Chen, Mingkai Wang, Fei Chao, Chenglin Wu, Shanshan Wang, Rongrong Ji, and Yonghong Tian
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
An Information Theory-Inspired Strategy for Automated Network Pruning
Xiawu Zheng, Yuexiao Ma, Teng Xi, Gang Zhang, Errui Ding, Yuchao Li, Jie Chen, Yonghong Tian, and Rongrong Ji
International Journal of Computer Vision, 2025
DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning
Xiawu Zheng, Chenyi Yang, Shaokun Zhang, Yan Wang, Baochang Zhang, Yongjian Wu, Yunsheng Wu, Ling Shao, and Rongrong Ji
International Journal of Computer Vision, 2023
MIGO-NAS: Towards Fast and Generalizable Neural Architecture Search
Xiawu Zheng, Rongrong Ji, Yuhang Chen, Qiang Wang, Baochang Zhang, Jie Chen, Qixiang Ye, Feiyue Huang, and Yonghong Tian
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
Evolving Fully Automated Machine Learning via Life-Long Knowledge Anchors
Xiawu Zheng, Yang Zhang, Sirui Hong, Huixia Li, Lang Tang, Youcheng Xiong, Jin Zhou, Yan Wang, Xiaoshuai Sun, Pengfei Zhu, Chenglin Wu, and Rongrong Ji
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
Joint algorithm and hardware optimization for edge inference adaptation and quantization.
I lead development of an automated compression framework for language and vision-language models, connecting core algorithms with GPU and Ascend deployment.
Collaboration on low-bit quantization and efficient deployment of automotive multimodal large models.
I lead acceleration, compression and low-bit quantization R&D for text-to-image and text-to-video models.
Research connecting model compression, compiler optimization and automated architecture search for cloud deployment.
Lightweight image enhancement research balancing reconstruction quality with mobile NPU and ISP constraints.
I lead lightweight smartphone image restoration research.
I lead R&D connecting mobile vision algorithms, compression and hardware adaptation.
Weight sparsification and joint sparse quantization; awarded Huawei's Product-Line-Level Outstanding Collaborative Project.
R&D experience in cross-age face recognition, city-scale vehicle retrieval and localization, and real-time face tracking.
R&D experience in compressed visual fingerprints, scene matching and fast localization.
Research on automated architecture search and compression strategies for efficient large-model deployment.
Postdoctoral research on architecture evaluation, efficient search and task adaptability.
Research on candidate architecture evaluation and selection with limited supervision.
Participation in Peng Cheng Cloud Brain platform construction and urgent R&D tasks.
Support for research development and team building in automated model design and efficient large-model deployment.
Alumni: 谢展豪 (Tencent; Qingyun Program); 王瑞霖 (Tencent; Qingyun Program); Yongdong Luo / 罗咏东 (Alibaba); Chenyu Zhou / 周陈昱 (Kuaishou); 蒋易耕 (Shanghai AI Laboratory); 许希威 (Talent program at a leading internet company (AI Infra))
PhD: Yuhang Wu / 吴宇航; Zhigang Chen / 陈志刚; Guilin Li / 李桂林; Weizhong Huang / 黄伟中; Wenjie Nie / 聂文杰; Xudong Li / 李旭东; Sibin Cai / 蔡思彬; Wang Chen / 陈旺
Master's: Haocheng Sun / 孙颢城; Yuhui Zeng / 曾宇晖; Haoxiang Wu / 吴豪翔; Kunpeng Liao / 廖锟鹏; Jing Xu / 许靖; Qingchuan Ma / 马晴川; Tianyu Xie / 谢天宇; Haoyu Huang / 黄皓禹; Chengwu Long / 龙成武; Xinxiong Wu / 吴鑫雄; Jinsen Su / 苏锦森; Yue Zhang / 张岳; Zheng Xuzhe / 郑旭哲; Zhuoqi Song / 宋卓奇; Xiaoyao Xie / 谢骁尧; Huaijia Kou / 寇怀佳; Dibo Lin / 林地波; Xinhai Ma / 马心海; Zhicheng Liu / 刘致成; Kefei Wu / 吴柯非; Yufei Jiao / 焦雨飞; Minghua Wu / 吴铭华; Yongbin Chen / 陈泳彬; Weijie Wei / 魏炜杰
Associate Editor, Pattern Recognition (March 2026–December 2029).
Area Chair: NeurIPS 2025, ICLR 2026 and PRCV 2025; accepted Area Chair appointments for ICLR 2027 and AAAI 2027.
ICML 2026 Silver Reviewer; ICLR 2025 Notable Reviewer.
Conference reviewing and program committee service includes CVPR, ICCV, ECCV, ICML, ICLR, NeurIPS, AAAI, ACM Multimedia and ACL Rolling Review.
Journal reviewing includes IEEE TPAMI, IJCV, IEEE TIP, IEEE TMM, IEEE MultiMedia, IEEE TCDS, ACM TOSEM, Engineering, Knowledge-Based Systems and Pattern Recognition; accepted a TMLR reviewer invitation.
Standardization contributions include GB/T 42382.1-2023 and the IEEE 2941 series. I received an IEEE SA Certificate of Appreciation for contributions to standardization; the IEEE 2941 working group in which I participated received the 2022 IEEE SA Emerging Technology Award.
Contributor to the 2024 Xiamen Science and Technology Progress Award (First Prize) and the 2025 Ministry of Education Engineering Technology Research Achievement Award (Second Prize).
Member of the Artificial Intelligence subcommittee of the Fourth National Committee for Computer Science and Technology Terminology.