Biography

I am affiliated with the Australian Artificial Intelligence Institute (AAII) at the University of Technology Sydney, where my research focuses on agentic AI, post-training, and foundation models, along with their applications in science and medicine. I have published over 50 peer-reviewed papers with 1100+ citations, with most of my first-author work appearing in top-tier venues, including conferences (NeurIPS, ICLR, ICML, ACM MM, AAAI, IJCAI, WWW, ICMR, MICCAI) and journals (IEEE TGRS, IEEE JBHI, IF, KBS, OE). I do research purely out of curiosity.

I bring over three years of industry experience in applied machine learning. I was a Research Associate in deep learning at the Shenzhen Institute of Meteorological Innovation, China (2021–2024), where I worked on real-world climate modeling based on remote-sensing data. In 2024, I was a visiting researcher at The Hong Kong Polytechnic University (PolyU), working on medical imaging processing.

I have delivered invited talks and tutorials, including Federated Intelligence in Web: A Tutorial at WWW 2025 (Sydney, Australia), Personalized Adapter for Large Meteorology Models on Devices at the FLFM Workshop @ AJCAI 2024 (Melbourne, Australia), and Federated Prompt Learning for Weather Foundation Models on Devices at the Main Track & AI4CI Workshop @ IJCAI 2024 (Jeju, South Korea).

I actively contribute to the research community as an Associate Editor of JESIT, and as a reviewer and Area Chair for numerous leading journals and conferences (e.g., TPAMI, TKDE, TNNLS, JMLR, NeurIPS, ICLR, ICML, CVPR, MM, KDD, AAAI, IJCAI), handling over 60 papers each year.

Research Interests

My long-term goal is to build general-purpose intelligent systems that learn from experience, reason through open-ended problems, and act reliably in the real world. I believe such systems can work alongside people as partners in discovery and expand the range of problems humanity can solve. Toward this goal, my work centers on three areas:

• Agentic AI: agents that plan, reason, and act over long horizons.
• Post-Training: improving language and vision-language models after pretraining through reinforcement learning and self-play.
• Foundation Models: models that learn at scale from distributed, heterogeneous data.

In addition, I extend these methods to applications in weather and climate, medical imaging, remote sensing, and scientific design.

Selected Publications  Google Scholar →

* indicates co-first authorship; indicates corresponding author.

Large-Scale Distributed Foundation Models

Pushing foundation models to learn at scale across distributed, privacy-sensitive data without ever centralizing it.

• Bi-Level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach
  Shengchao Chen, Guodong Long, Dikai Liu, Jing Jiang
  arXiv preprint arXiv:2604.06727 [Preprint], 2026.
• FeDaL: Federated Dataset Learning for General Time Series Foundation Models
  Shengchao Chen, Guodong Long, Michael Blumenstein, Jing Jiang
  The Fourteenth International Conference on Learning Representations (ICLR) [Core A*/CCF-A], 2026.
• Federated Foundation Models on Heterogeneous Time Series
  Shengchao Chen, Guodong Long, Jing Jiang, Chengqi Zhang
  Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI) [Core A*/CCF-A], 2025.
• Federated Intelligence in Web: A Tutorial
  Peng Yan*, Shengchao Chen*, Guodong Long*
  Companion Proceedings of the ACM on Web Conference (WWW) [Core A*/CCF-A], 2025.
• Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
  Shengchao Chen, Guodong Long, Jing Jiang, Chengqi Zhang
  Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS) [Core A*/CCF-A], 2024.
• Federated Prompt Learning for Weather Foundation Models on Devices
  Shengchao Chen, Guodong Long, Tao Shen, Jing Jiang, Chengqi Zhang
  The 33rd International Joint Conference on Artificial Intelligence (IJCAI) [Core A*/CCF-A], 2024.
• Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data
  Shengchao Chen, Guodong Long, Tao Shen, Jing Jiang, Chengqi Zhang
  The 32rd International Joint Conference on Artificial Intelligence (IJCAI) [Core A*/CCF-A], 2023.

Agentic RL & VLM/LLM Post-training

Training agentic language and vision-language models to plan, act, and improve through reinforcement learning.

• Policy-Adaptive Credit Assignment for Spatial Reasoning with Verifiable Rewards
  Hailiang Yang, Shengchao Chen (Project Leader)
  arXiv preprint arXiv:2610.26410 [Preprint], 2026.
• LURE: Pursuit-Evasion Self-Play for Zero-Data Multi-Step Reasoning
  Jing Yu, Shengchao Chen (Project Leader), Yiyun Tan
  arXiv preprint arXiv:2608.21871 [Preprint], 2026.
• Hider–Seeker Self-Play: Geometry-Verifiable Process Rewards for Long-Horizon Visual Search
  Yu Mao, Shengchao Chen (Project Leader)
  Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) [Core A*/CCF-A], 2026.
• AtmoZero: Self-Play Post-Training for Caption-Free Weather Time-Series Captioning
  Qirui Zheng, Shengchao Chen (Project Leader)
  Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) [Core A*/CCF-A], 2026.

Agent for Scientific Design

Building autonomous agents that reason, critique, and iterate their way to better scientific and engineering designs.

• PCFBench: How Far Can Large Vision-Language Models Go in Physics-Aware Photonic Inverse Design?
  Shengchao Chen, Ting Shu, Sufen Ren
  Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) [Core A*/CCF-A], 2026.
• The Physicist, the Coder, and the Critic: Agentic Photonic Crystal Fiber Inverse Design via Verbal Gradient Descent
  Shengchao Chen, Ting Shu
  Association for Computational Linguistics: EMNLP 2026 (EMNLP) [Core A*/CCF-B].
• Learning Design Skills as Memory Policies for Agentic Photonic Inverse Design
  Shengchao Chen, Ting Shu, Sufen Ren
  Knowledge-Based Systems (KBS) [JCR Q1/TOP], 2026. / ICML 2026 AI for Physics
• PCF-LLM: Scaling LLMs for Multimodal Understanding of Structured Scientific Data in Photonic Crystal Fiber Sensors
  Shengchao Chen, Geyao Hu, Sufen Ren, Ting Shu
  Information Fusion, 104022, 2025. [JCR Q1/TOP, 5-Yr IF 19.9]

Trustworthy Medical AI

Building AI that clinicians can trust, bridging the gap between algorithmic performance and real clinical impact.

• Visual and Textual Spaces Both Matter: Taming CLIP for Non-IID Federated Medical Image Classification
  Lulu Feng, Shengchao Chen
  Knowledge-Based Systems (KBS) [JCR Q1/TOP], 2026.
• FM²: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imaging
  Shengchao Chen, Ting Shu
  The 34th ACM International Conference on Multimedia (ACM MM) [Core A*/CCF-A], 2026.
• Restyled, Tuning, and Alignment: Taming VLMs for Federated Non-IID Medical Image Analysis
  Shengchao Chen, Ting Shu
  International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) [Core A/CCF-B], 2025.
• Taming Vision-Language Models for Foundation Models on Heterogeneous Medical Imaging Modalities
  Lulu Feng, Shengchao Chen
  The 15th ACM International Conference on Multimedia Retrieval (ICMR) [Core B/CCF-B], 2025.
• Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia from Chest X-Ray Images
  Shengchao Chen, Sufen Ren, Guanjun Wang, Mengxing Huang, Chenyang Xue
  IEEE Journal of Biomedical and Health Informatics (IEEE JBHI) [JCR Q1/TOP], 2024.
• Ensemble Learning for Retinal Disease Recognition under Limited Resources
  Jian Wang, Hui Peng, Shengchao Chen, Sufen Ren
  Medical & Biological Engineering & Computing 62 (9), 2839-2852, 2024. [JCR Q2]

Remote Sensing Intelligence

Turning raw signals from sky and space into real-time, actionable understanding of a changing planet.

• Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Framework
  Shengchao Chen, Ting Shu, Huan Zhao, Jiahao Wang, Sufen Ren, Lina Yang
  Knowledge-Based Systems (KBS) [JCR Q1/TOP], 2024.
• MASK-CNN-Transformer for Real-Time Multi-Label Weather Recognition
  Shengchao Chen, Ting Shu, Huan Zhao, Yuan Yan Tang
  Knowledge-Based Systems (KBS) [JCR Q1/TOP], 2023.
• TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression
  Shengchao Chen, Ting Shu, Huan Zhao, Guo Zhong, Xunlai Chen
  IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS) [JCR Q1/TOP], 2023.
• Dynamic Multiscale Fusion Generative Adversarial Network for Radar Image Extrapolation
  Shengchao Chen, Ting Shu, Huan Zhao, Qilin Wan, Jincan Huang, Cailing Li
  IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS) [JCR Q1/TOP], 2022.

Early AI for Science Work

Treating AI as a scientific instrument that can reason, design, and discover alongside human experts.

• Towards Scalable and Accurate Property Prediction for Photonic Crystal Fibers with Federated Learning
  Guanjun Wang, Jiacheng Liu, Shengchao Chen, Sufen Ren
  Optics Express 33 (16), 33421-33434, 2025. [JCR Q1]
• Optimizing Low-Resolution Spectral Demodulation for Long-Period Fiber Gratings Using Residual Convolutional Neural Networks
  Guanjun Wang, Jiacheng Liu, Shengchao Chen, Sufen Ren
  Optics Express 33 (4), 8225-8238, 2025. [JCR Q1]
• Towards Robust Machine Learning-Based LPFG Temperature Sensing Demodulation with Limited Data via Diffusion Models
  Guanjun Wang, Jianxun Liu, Shengchao Chen, Sufen Ren
  Optics Communications, 132263, 2025. [JCR Q2]
• Federated Learning-Based Wavelength Demodulation System for Multi-Point Distributed Multi-Peak FBG Sensors
  Xuan Hou, Sufen Ren, Kebei Yu, Yule Hu, Haoyang Xu, Chenyang Xue, Shengchao Chen, Guanjun Wang
  Optics Express 32 (23), 41297-41313, 2024. [JCR Q1]
• Collaborative Photonic Crystal Fiber Property Optimization: A New Paradigm for Reverse Design
  Shengchao Chen, Xinchen Wang, Sufen Ren, Jianli Yang, Yaqian Zhang, Guanjun Wang
  IEEE Photonics Technology Letters 35 (19), 1035-1038, 2023. [JCR Q2]
• Efficient Calculation of Optical Properties of Suspended-Core Fiber via a Machine Learning Algorithm
  Shuyu Yuan*, Shengchao Chen*, Jianli Yang, Qian Yang, Sufen Ren, Guanjun Wang, Benguo Yu
  Applied Optics 61 (19), 5714-5721, 2022. [JCR Q2]
• Fabry-Perot Interferometric Sensor Demodulation System Utilizing Multi-Peak Wavelength Tracking and Neural Network Algorithm
  Shengchao Chen, Feifan Yao, Sufen Ren, Jianli Yang, Qian Yang, Shuyu Yuan, Guanjun Wang, Mengxing Huang
  Optics Express 30 (14), 24461-24480, 2022. [JCR Q1]
• Cost-Effective Improvement of the Performance of AWG-Based FBG Wavelength Interrogation via a Cascaded Neural Network
  Shengchao Chen, Feifan Yao, Sufen Ren, Guanjun Wang, Mengxing Huang
  Optics Express 30 (5), 7647-7663, 2022. [JCR Q1]
• Reconstruction of Fabry-Perot Interferometric Sensor Spectrum from Extremely Sparse Sampling Points Using Dense Neural Network
  Shengchao Chen, Sufen Ren, Jianli Yang, Feifan Yao, Qian Yang, Lu Wang, Guanjun Wang, Mengxing Huang
  IEEE Photonics Technology Letters 34 (24), 1337-1340, 2022. [JCR Q2]

Awards & Honors

• AAII Best Student Paper Award – 1 of 3 awarded annually, top 1.5% of ~200 AAII PhD students (UTS) 2025
• Outstanding Master's Thesis (Provincial) – Top 0.05% provincewide 2025
• National Scholarship – Top 0.1% nationally, 1/1,218 (Ministry of Education, China) 2022
• Outstanding Master's Thesis – 1st of 3 recipients, top 1.4% of 210 in cohort 2023
• Outstanding Graduates – Ranked 1st in college 2023
• Outstanding Graduate Student – Ranked 1st in college 2022

Academic Services

Associate Editor

• JESIT, Journal of Electrical Systems and Information Technology.

Area Chair

• IJCNN, International Joint Conference on Neural Networks.
• ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing.

Conference Reviewer / PC Member

• NeurIPS, Neural Information Processing Systems [Core A*].
• ICML, International Conference on Machine Learning [Core A*].
• ICLR, International Conference on Learning Representations [Core A*].
• AAAI, AAAI Conference on Artificial Intelligence [Core A*].
• IJCAI, International Joint Conference on Artificial Intelligence [Core A*].
• CVPR, Computer Vision and Pattern Recognition [Core A*].
• ECCV, European Conference on Computer Vision [Core A*].
• MICCAI, Medical Image Computing and Computer Assisted Intervention [Core A].
• KDD, ACM SIGKDD Conference on Knowledge Discovery and Data Mining [Core A*].
• ECAI, European Conference on Artificial Intelligence [Core A].
• ICASSP, IEEE Int. Conf. on Acoustics, Speech and Signal Processing [Core B].
• ICME, IEEE Int. Conf. on Multimedia and Expo [Core A].
• ICCV, International Conference on Computer Vision [Core A*].
• WWW, The Web Conference [Core A*].
• MM, ACM International Conference on Multimedia [Core A*].
• WSDM, ACM International Conference on Web Search and Data Mining [Core A].
• WACV, IEEE/CVF Winter Conference on Applications of Computer Vision [Core A].
• AISTATS, International Conference on Artificial Intelligence and Statistics [Core A].
• PAKDD, Pacific-Asia Conference on Knowledge Discovery and Data Mining [Core B].

Journal Reviewer

• JMLR, Journal of Machine Learning Research.
• Machine Learning, Machine Learning (Springer).
• TPAMI, IEEE Transactions on Pattern Analysis and Machine Intelligence.
• TNNLS, IEEE Transactions on Neural Networks and Learning Systems.
• TKDE, IEEE Transactions on Knowledge and Data Engineering.
• TGRS, IEEE Transactions on Geoscience and Remote Sensing.
• TETC, IEEE Transactions on Emerging Topics in Computing.
• KBS, Knowledge-Based Systems.
• AIM, Artificial Intelligence in Medicine.
• Information Systems, Information Systems (Elsevier).
• Computer Networks, Computer Networks (Elsevier).
• TMI, IEEE Transactions on Medical Imaging.
• TDSC, IEEE Transactions on Dependable and Secure Computing.
• TCE, IEEE Transactions on Consumer Electronics.
• TII, IEEE Transactions on Industrial Informatics.
• TMLR, Transactions on Machine Learning Research.
• TIST, ACM Transactions on Intelligent Systems and Technology.