👤 Biography
Rongyu is a third-year dual Ph.D. candidate at Nanjing University and The Hong Kong Polytechnic University, where he is co-supervised by Prof. Yuan Du, Prof. Li Du, and Prof. Dan Wang. He is also a visiting student at Peking University under the supervision of Prof. Shanghang Zhang. Previously, he received the M.Phil. degree from The Chinese University of Hong Kong, Shenzhen, supervised by Prof. Fangxin Wang, the B.Mang. and B.Eng. degree from the joint program of Beijing University of Posts and Telecommunications and Queen Mary University of London. He has published over 10 papers in top-tier CCF-A and CAS-Q1 international conferences and journals such as Nature Computational Science, CVPR, AAAI, TMC, and TCSVT, etc.
Feel free to reach out, or learn more from My CV.
🔬 AI Researcher
- Research focus on efficient and generalization learning
- Efficiency: Dynamic Neural Network
- Multimodal Generalization: Embodied AI including Robotics and Autonomous Driving
✍️ Given Credits
☎️ Contact Info
- Address: Room 2728, Science Building No. 2, Peking University, Beijing, China
- Phone: +(86) 188-1305-1303
- Email:
royz981203@hotmail.com rongyu.zhang@connect.polyu.hk
🎓 Educations
The Hong Kong Polytechnic University (2023.09-Present) Dual Ph.D. in Computing Science
Nanjing University (2023.09-Present) Dual Ph.D. in Electrical Science and Technology
The Chinese University of Hong Kong, Shenzhen (2021.09-2023.03) M.Phil. in Computer and Information Engineering
Beijing University of Posts and Telecommunications (2017.09-2021.06) Dual B.Mang. in E-Commerce Engineering with Law
Queen Mary University of London (2017.09-2021.06) Dual B.Eng. in Electrical Engineering and Computer Sciences
🔥 News
📌 We have several academic intern positions at HMI Lab (Peking University). We actively work on AI4Science and Embodied AI. If you like what we do, don't hesitate to contact me.
[09.2025] 🎉 One paper Orochi was accepted by NeurlPS as Spotlight (CCF-A).
[05.2025] 📕 I am selected for the “Endeavor Scholarship — Integrated Circuit Talent Development Program” of China Education Development Foundation (93 recipients nationwide).
[05.2025] 🎉 One paper INIF was accepted by Nature Computational Science (CAS-Q1).
[05.2025] 🎉 One paper UTMP was accepted by IEEE TMC (CCF-A) as first author.
[05.2025] 🎉 One paper EVA was accepted by ICML 2025 (CCF-A).
[04.2025] 🎉 One paper FBQuant was accepted by IJCAI 2025 (CCF-A).
[04.2025] 🎉 One paper RepCaM++ was accepted by IEEE TMC (CCF-A) as first author.
[03.2025] 💻 PAT (AAAI'25) has been applied to Samsung’s on-device applications for smartphones and TVs.
[01.2025] 📕 I am selected for the First session “Young Talent Support Project Doctoral Special Program” of China Association for Science and Technology (3,226 recipients nationwide)
[12.2024] 🎉 One paper BEVUDA++ was accepted by IEEE TCSVT (CAS-Q1) as first author.
[12.2024] 🎉 One paper PAT was accepted by AAAI 2025 (CCF-A).
[12.2024] 🏅 I was named "Outstanding Ph.D. Candidate" by NJU.
[11.2024] 💰 I was offered "Bank of Jiangsu" Scholarship from NJU.
[09.2024] 💻 The Panasonic Corporation is integrating the VeCAF (MM'24) into its actual business operations.
[08.2024] 💼 I joined the Beijing Academy of Artificial Intelligence supervised by Prof. Shanghang Zhang.
[07.2024] 🎉 One paper VeCAF was accepted by ACMMM 2024 (CCF-A) as first author.
[07.2024] 🎓 I am offered a dual Ph.D. at The Hong Kong Polytechnic University supervised by Prof. Dan Wang.
[05.2024] 🎉 One paper MuPFL was accepted by IEEE TMC (CCF-A) as first author.
[04.2024] 📕 Our project: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation, has been selected as one of the Jiangsu Province Graduate Research and Practical Innovation Projects.
[03.2024] 💻 The Panasonic Corporation is integrating the MoFME (AAAI'24) into its actual business operations.
[01.2024] 🎉 One paper BEVUDA was accepted by IEEE ICRA 2024 (CCF-B) as first author.
[12.2023] 🎉 One paper MoFME was accepted by AAAI 2024 (CCF-A) as first author.
[08.2023] 🏅 We won 2nd place in the SHIFT Challenge 2023 - Continuous Test-time Adaptation for Semantic Segmentation in the challenges of VCL Workshop, ICCV2023.
[06.2023] 🎓 I joined the ISCL lab at Nanjing University and the HMI Lab of the NATIONAL ENGINEERING RESEARCH CENTER OF VISUAL TECHNOLOGY at Peking University as a joint Ph.D. student.
[03.2023] 🎓 I received M.Phil. degree from The Chinese University of Hong Kong, Shenzhen
[03.2023] 🎉 One paper RepCaM was accepted by ACM NOSSDAV 2023 (CCF-B) as first author.
[03.2023] 🎉 One paper CdFed was accepted by IEEE ICME 2023 (CCF-B) as first author.
[03.2023] 🎉 One paper FedFHN was accepted by IEEE Network (CAS-Q2) as first author.
[03.2023] 🎉 One paper FedAB was accepted by IEEE IoTJ (CAS-Q1).
[03.2023] 🎉 Two papers BEVSAN and CDCCA were accepted by IEEE CVPR 2023 (CCF-A).
[09.2022] 💼 I joined OPPO Research as a Research Intern.
[08.2021] 🎓 I joined INML lab at The Chinese University of Hong Kong, Shenzhen as an M.Phil. student.
📝 Publications
📒 Selected publications




Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation

VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
📚 Full publications
*: Equal Contribution.
CCF-A/CAS-Q1 as First-author:
-
NIPS'25 Orochi: Versatile Biomedical Image Processor (Spotlight)
Gaole Dai, Chenghao Zhou, Yu Zhou, Rongyu Zhang, Yuan Zhang, Chengkai Hou, Tiejun Huang, Jianxu Chen, Shanghang Zhang
Neural Information Processing Systems
-
NCS'24 Implicit Neural Image Field for Biological Microscopy Image Compression
Gaole Dai, Rongyu Zhang*, Cheng-Ching Tseng*, Qingpo Wuwu*, Shaokang Wan*, Ming Lu, Tiejun Huang, Yu Zhou, Ali Ata Tuz, Matthias Gunzer, Jianxu Chen, Shanghang Zhang
Nature Computational Science
-
TMC'25 Unimodal Training-Multimodal Prediction: Cross-modal Federated Learning with Hierarchical Aggregation
Rongyu Zhang, Xiaowei Chi, Wenyi Zhang, Guiliang Liu, Dan Wang, Fangxin Wang
IEEE Transactions on Mobile Computing
-
ICML'25 EVA: An Embodied World Model for Future Video Anticipation
Xiaowei Chi, Hengyuan Zhang, Chun-Kai Fan, Xingqun Qi, Rongyu Zhang, Anthony Chen, Chi-min Chan, Wei Xue, Wenhan Luo, Shanghang Zhang, Yike Guo
International Conference on Machine Learning
-
IJCAI'25 FBQuant: FeedBack Quantization for Large Language Models
Yijiang Liu, Hengyu Fang, Liulu He, Rongyu Zhang, Yichuan Bai, Yuan Du, Li Du
International Joint Conference on Artifical Intelligence
-
TMC'25 RepCaM++: Exploring Transparent Visual Prompt with Inference-time Re-parameterization for Neural Video Delivery
Rongyu Zhang, Xize Duan, Jiaming Liu, Li Du, Yuan Du, Dan Wang, Shanghang Zhang, Fangxin Wang
IEEE Transactions on Mobile Computing
-
AAAI'25 PAT: Pruning-Aware Tuning for Large Language Models
Yijiang Liu, Huanrui Yang, Youxin Chen, Rongyu Zhang, Miao Wang, Yuan Du, Li Du
AAAI Conference on Artificial Intelligence
-
TCSVT'25 BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection
Rongyu Zhang, Jiaming Liu, Xiaoqi Li, Xiaowei Chi, Dan Wang, Li Du, Yuan Du, Shanghang Zhang
IEEE Transactions on Circuits and Systems for Video Technology
-
AAAI‘24 Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation
Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang
AAAI Conference on Artificial Intelligence
-
MM'24 VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
Rongyu Zhang*, Zefan Cai*, Huanrui Yang*, Zidong Liu, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Baobao Chang, Yuan Du, Li Du, Shanghang Zhang
ACM International Conference on Multimedia
-
TMC'24 Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data
Rongyu Zhang, Yun Chen, Chenrui Wu, Fangxin Wang, Bo Li
IEEE Transactions on Mobile Computing
-
ICRA'24 BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection
Jiaming Liu*, Rongyu Zhang*, Xiaowei Chi, Xiaoqi Li, Ming Lu, Yandong Guo, Shanghang Zhang
International Conference on Robotics and Automation
-
Noss'23 RepCaM: Re-parameterization Content-aware Modulation for Neural Video Delivery
Rongyu Zhang*, Lixuan Du*, Jiaming Liu*, Congcong Song, Fangxin Wang, Xiaoqi Li, Ming Lu, Yandong Guo, Shanghang Zhang
ACM Network and Operating System Support for Digital Audio and Video
-
ICME'23 Cluster-driven GNN-based Federated Recommendation System with Biased Message Dropout
Rongyu Zhang*, Yun Chen*, Chenrui Wu, Fangxin Wang
IEEE International Conference on Multimedia and Expo.
-
Netw'23 Optimizing Efficient Personalized Federated Learning with Hypernetworks at Edge
Rongyu Zhang, Yun Chen, Chenrui Wu, Fangxin Wang, Jiangchuan Liu
IEEE Network
-
CVPR'23 Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-world
Yulu Gan, Mingjie Pan, Rongyu Zhang, Zijian Ling, Lingran Zhao, Jiaming Liu, Shanghang Zhang
The IEEE/CVF Conference on Computer Vision and Pattern Recognition
-
CVPR'23 BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks
Xiaowei Chi, Jiaming Liu, Ming Lu, Rongyu Zhang, Zhaoqing Wang, Yandong Guo, Shanghang Zhang
The IEEE/CVF Conference on Computer Vision and Pattern Recognition
-
IoTJ'23 FedAB: Truthful Federated Learning with Auction-based Combinatorial Multi-armed Bandit
Chenrui Wu, Yifei Zhu, Rongyu Zhang, Yun Chen, Fangxin Wang, Shuguang Cui
IEEE Internet of Things Journal
-
arXiv'25 MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation
Rongyu Zhang*, Menghang Dong*, Yuan Zhang*, Liang Heng, Xiaowei Chi, Gaole Dai, Li Du, Dan Wang, Yuan Du, Shanghang Zhang
-
arXiv'25 T-REX: Mixture-of-Rank-One-Experts with semantic-aware Intuition for Multi-task Large Language Model Finetuning
Rongyu Zhang*, Yijiang Liu*, Huanrui Yang*, Shenli Zheng, Chongkang Tan, Dan Wang, Yuan Du, Li Du, Shanghang Zhang
-
arXiv'24 Decomposing the Neural: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
Rongyu Zhang*, Aosong Cheng*, Yulin Luo*, Gaole Dai, Huanrui Yang, Jiaming Liu, Ran Xu, Li Du, Yuan Du, Yanbing Jiang, Shanghang Zhang
-
arXiv'24 M2Chat: Empowering VLM for Multimodal LLM Interleaved Text-Image Generation
Xiaowei Chi*, Rongyu Zhang*, Zhengkai Jiang, Yijiang Liu, Yatian Wang, Xingqun Qi, Wenhan Luo, Peng Gao, Shanghang Zhang, Qifeng Liu, Yike Guo
-
arXiv'24 ViML: A Video, Music, Language Unified Dataset for Understanding and Generation
Xiaowei Chi, Aosong Chen, Pengjun Fang, Yatian Wang, Zeyue Tian, Yingqing He, Zhaoyang Liu, Xingqun Qi, Rongyu Zhang, Mengfei Li, Jiahao Pan, Yanbing Jiang, Wei Xue, Wenhan Luo, Qifeng Chen, Shanghang Zhang, Qifeng Liu, Yike Guo
🥇 Honors and Awards
- (2025.09): Hong Kong Post-Graduate Scholarship (HKPGS) with 18,840¥/month, The Hong Kong Polytechnic University
- (2025.05): The “Endeavor Scholarship — Integrated Circuit Talent Development Program (93 recipients nationwide)” with 100,000¥, China Education Development Foundation (中国教育发展基金会“奋进奖学金—集成电路人才培养”项目;全国93人入选)
- (2025.01): The First Session “Young Talent Support Project Doctoral Special Program (3,226 recipients nationwide)” with 40,000¥, China Association for Science and Technology (首届中国科协“青年人才托举工程博士生专项”计划;全国3,226人入选)
- (2024.12): Outstanding Ph.D. Candidate with 2,000¥/year, Nanjing University
- (2024.12): “Bank of Jiangsu” Scholarship with 5,000¥, Nanjing University
- (2024.05): Jiangsu Province Graduate Research and Practical Innovation Project “Mixture-of-Activation-Sparsity-Experts for Continuous Test-time Adaptation” with 15,000¥, Jiangsu Provincial Department of Education (江苏省”研究生科研与实践创新”计划)
- (2023.10): The 2nd place of the SHIFT Challenge 2023 - Continuous Test-time Adaptation for Semantic Segmentation in the challenges of VCL Workshop with 2,000$, International Conference on Computer Vision
💼 Services
Journal reviewer
- IEEE Transactions on Mobile Computing (TMC)
- IEEE Transactions on Computers (TC)
- IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
- IEEE Transactions on Dependable and Secure Computing (TDSC)
- IEEE Internet of Things Journal (IoTJ)
- IEEE Transactions on Communications (TCOM)
- IEEE Network Magazine (Network)
Conference reviewer
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
- ACM International Conference on Multimedia (MM) 2024, 2025
- IEEE/CVF International Conference on Computer Vision (ICCV) 2023, 2025
- Annual Conference on Neural Information Processing Systems (NeurIPS) 2025
- The Fortieth AAAI Conference on Artificial Intelligence (AAAI) 2026
💻 Internships
- Beijing Academy of Artificial Intelligence (2024.08-2024.11) Research Intern, supervised by Prof. Shanghang Zhang
- OPPO Research Institute (2022.09-2023.03) Research Intern, supervised by Dr. Yandong Guo
- LENOVO Research Institute (2020.11-2021.05) Research Intern, supervised by Prof. Jiangtao Gong
🎤 Talks
- ‘Research on Key Technologies for Improving the Performance and Efficiency of On-device Models Based on Mixture-of-Experts’ @ The Chinese University of Hong Kong, Shenzhen, invited by Prof. Fangxin Wang (2025.08.05) Slides
🧑🏫 Teaching
Teaching Assistant at PolyU
- COMP 6704: Advanced Machine Learning
😄 Miscellaneous
❤️ Family
- I have a beautiful girlfriend, Ziqi Qiao, who is also a Ph.D. student at Peking University. We also own an adorable cat 🐱 named QiuQiu. He brings us tremendous fun and happiness.

🧑🤝🧑 Friends
- My closest academic friends: Jiaming Liu, Yulin Luo, Yuan Zhang, and Gaole Dai from PKU; Xiaowei Chi from HKUST; Yijiang Liu from NJU; Chenrui Wu from ZJU&SFU; Yili Jin and Kaiyuan Hu from McGill.

😄 Hobbies
- I am a crazy basketball 🏀 & football ⚽️ fan. I enjoy the games of Kevin Durant 🕷️ and Kyrie Irving 🧙. I also wholeheartedly pledge my allegiance to Chelsea Football Club, KTBFFH! 💙
