About Me

I am a Youth Researcher at Shanghai AI Laboratory. I received my Ph.D. in 2026 through the joint program of Shanghai Jiao Tong University and Eastern Institute of Technology, Ningbo, advised by Prof. Yuntian Chen (in the group of Prof. Dongxiao Zhang, guided by Prof. Shiyi Chen) and Prof. Xiaokang Yang. I also collaborate closely with Prof. Chao Ma.

I received my B.E. and M.S. degrees from Northwestern Polytechnical University in 2019 and 2022, supervised by Prof. Junwei Han and Prof. Xiwen Yao.

My research focuses on self-evolving AI agents, autonomous scientific research, and AI for Science. My earlier work studies data-limited and domain-aware visual learning — how prior knowledge, task structure, and foundation models can be systematically integrated to build generalizable and trustworthy vision systems under limited supervision. I work on few-shot & open-vocabulary segmentation, prompt learning, and parameter-efficient fine-tuning (PEFT), with applications in remote sensing, medical imaging, and AI for Science. I am now interested in turning real tasks, environment interaction, and verifiable feedback into capabilities that keep growing.

Honors & Awards

2026 · Shanghai Outstanding Graduate
2025 · Young Talent Support Program for Doctoral Students, China Association for Science and Technology (CAST)
2024 · National Scholarship for Doctoral Students
2024 · Award Winner, IJCAI 2024 Fast Aerodynamic Drag Prediction Challenge
2021 · Second Prize, “Intelligent Arrow & Fire Eye” Artificial Intelligence Challenge, CASIC

News

Jun. 2026 ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research released on arXiv. [Paper]
Mar. 2026 Contributed to Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale. [Paper]
Jan. 2026 Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning released on arXiv. [Paper]
Nov. 2025 Paper accepted at AAAI 2026: Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame. [Paper]
Apr. 2025 Paper published in IEEE TGRS: Open-Vocabulary Remote Sensing Image Semantic Segmentation. [Paper] [Code]
Apr. 2025 Paper published in IEEE TGRS: HSFormer: Multiscale Hybrid Sparse Transformer for Uncertainty-Aware Cloud and Shadow Removal. [Paper]
2025 Paper published in Nexus (Cell Press): Generalized Domain Prompt Learning for Accessible Scientific Vision-Language Models. [Paper] [Code]
Feb. 2025 Co-first-authored paper accepted at AAAI 2025: Auto-Regressive Moving Diffusion Models for Time Series Forecasting. [Paper] [Code]
Sep. 2024 Paper published in Physics of Fluids: Vision-Informed Flow Field Super-Resolution with Quaternion Spatial Modeling and Dynamic Fluid Convolution. [Paper] [Code]
Jun. 2024 Paper accepted at CVPR 2024: Domain Prompt Learning with Quaternion Networks. [Paper] [Code]

Research Interests

Self-Evolving AI Agents: Learning from tasks, tools, environments, and verifiable feedback
Autonomous Scientific Research: Agents for literature understanding, experimentation, analysis, and discovery
AI for Science: Deep learning for scientific discovery and simulation
Data-Limited Learning: Few-shot learning, prompt learning, and parameter-efficient fine-tuning
Computer Vision: Image segmentation, object detection, and classification
Remote Sensing: AI-powered analysis of satellite and aerial imagery

Background

Shanghai Jiao Tong University & Eastern Institute of Technology, Ningbo · Shanghai / Ningbo, China
Ph.D. in Computer Science · Sept. 2022 – Jun. 2026
Northwestern Polytechnical University · Xi'an, China
M.S. in Pattern Recognition and Intelligent Systems · Sept. 2019 – Mar. 2022
Northwestern Polytechnical University · Xi'an, China
B.E. in Automation · Sept. 2015 – Jun. 2019

Invited Talks and Presentations

2025, Domain Prompt Learning, IJCAI 2025 (Best Paper from Sister Conference Track), Shenzhen, China.
2025, Generalized Domain Prompt Learning for Accessible Scientific Vision-Language Models, CUE 2025, Kitakyushu, Japan.
2025, Auto-Regressive Moving Diffusion Models for Time Series Forecasting, AAAI 2025, Philadelphia, USA.
2024, Data-Limited Scientific Visual Learning, The 13th Ningbo Academic Conference, Ningbo, China.
2024, Vision-Informed Flow Field Super-Resolution, The First National Conference on Intelligent Fluid Mechanics, Xi’an, China.
2024, Fast Aerodynamic Drag Prediction with Transformer Solvers, IJCAI 2024, Jeju, South Korea.
2024, Domain Prompt Learning with Quaternion Networks, CVPR 2024, Seattle, USA.
2024, Rock Reconstruction with Deep Generative Networks, EGU, Vienna, Austria.
2024, Domain-Controlled Prompt Learning, AAAI 2024, Vancouver, Canada.

Publications

KDD 2026

Sci-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification

Xiangyu Zhao, Hengyuan Zhao, Yiheng Wang, Wanghan Xu, Yuhao Zhou, Qinglong Cao, Zhiwang Zhou, Lei Bai, Wenlong Zhang, Xiao-Ming Wu

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026).

PDF
PR 2026

Dual-perspective Filter Pruning via Diversity and Independence Collaboration

C. Gao, Qinglong Cao, X. Yao, X. Feng, G. Cheng

Pattern Recognition (PR), 177:113321, 2026.

Paper
ECM:X 2026

Enhancing Photovoltaic Power Forecasting with Cross-Variable Linear Integrated Enhanced Transformer

Jiaxin Gao, Qinglong Cao, Yinghao Chu, Dongxiao Zhang, Yuntian Chen

Energy Conversion and Management: X, 2026.
ICASSP 2026

MoE-AMC: Enhancing Automatic Modulation Classification Performance Using Mixture-of-Experts

J. Gao, Qinglong Cao, Y. Chen

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026).

PDF
ICLR 2026

Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation

Z. Zhou, Y. Pu, X. He, Y. Liu, Y. Chen, J. Gong, Qinglong Cao, et al.

International Conference on Learning Representations (ICLR 2026).

PDF
AAAI2026

Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame

Qinglong Cao, Xirui Li, Ding Wang, Chao Ma, Yuntian Chen, Xiaokang Yang

Association for the Advancement of Artificial Intelligence (AAAI 2026), February 2026.

PDF
TGRS 2026

Leveraging Pretrained Diffusion Model for Semantic 3D Reconstruction from Monocular Remote Sensing Image

Xin Xu, Ruizhe Deng, Qinglong Cao, Zhiling Guo, Yuntian Chen, Jinyue Yan

IEEE Transactions on Geoscience and Remote Sensing (TGRS), 64:5603516, January 2026.
TGRS

Open-Vocabulary Remote Sensing Image Semantic Segmentation

Qinglong Cao, Yuntian Chen, Chao Ma, Xiaokang Yang

IEEE Transactions on Geoscience and Remote Sensing (TGRS), April 2025.

PDF Code
RENE

OpenWPF: A Cross-Dataset Benchmark for Neural Network-Based Wind Power Forecasting

Xin Xu, Qinglong Cao, Ruizhe Deng, Zhiling Guo, Yuntian Chen, Jinyue Yan

Renewable Energy (RENE), April 2025.

PDF
TGRS

HSFormer: Multiscale Hybrid Sparse Transformer for Uncertainty-Aware Cloud and Shadow Removal

Changqi Sun, Yuntian Chen, Qinglong Cao, Longfeng Nie, Zhenzhong Zeng, Dongxiao Zhang

IEEE Transactions on Geoscience and Remote Sensing (TGRS), April 2025.

PDF
Nexus

Generalized Domain Prompt Learning for Accessible Scientific Vision-Language Models

Qinglong Cao, Yuntian Chen, Lu Lu, Hao Sun, Zhenzhong Zeng, Xiaokang Yang, Dongxiao Zhang

Nexus, Cell Press, 2025.

PDF Code
AAAI2025

Auto-Regressive Moving Diffusion Models for Time Series Forecasting

Jiaxin Gao, Qinglong Cao (Co-first Author), Yuntian Chen

Association for the Advancement of Artificial Intelligence (AAAI 2025), February 2025.

PDF Code
POF

Vision-Informed Flow Field Super-Resolution with Quaternion Spatial Modeling and Dynamic Fluid Convolution

Qinglong Cao, Yuntian Chen, Ding Wang, Zhengqin Xu, Chao Ma, Xiaokang Yang, Shiyi Chen

Physics of Fluids (POF), September 2024.

PDF Code
CVPR2024

Domain Prompt Learning with Quaternion Networks

Qinglong Cao, Zhengqin Xu, Yuntian Chen, Chao Ma, Xiaokang Yang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2024), June 2024.

PDF Code
AAAI2024

Domain-Controlled Prompt Learning

Qinglong Cao, Zhengqin Xu, Yuntian Chen, Chao Ma, Xiaokang Yang

Association for the Advancement of Artificial Intelligence (AAAI 2024), February 2024.

PDF Code
TGRS

Few-Shot Rotation-Invariant Aerial Image Semantic Segmentation

Qinglong Cao, Yuntian Chen, Chao Ma, Xiaokang Yang

IEEE Transactions on Geoscience and Remote Sensing (TGRS), December 2023.

PDF Code
TCSVT

Break the Bias: Delving Semantic Transform Invariance for Few-Shot Segmentation

Qinglong Cao, Yuntian Chen, Chao Ma, Xiaokang Yang

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), October 2023.

PDF Code
arXiv

Progressively Dual Prior Guided Few-shot Semantic Segmentation

Qinglong Cao, Yuntian Chen, Xiwen Yao, Junwei Han

arXiv, November 2022.

PDF Code
TNNLS

Learning to Assess Image Quality Like an Observer

Xiwen Yao, Qinglong Cao, Xiaoxu Feng, Gong Cheng, Junwei Han

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), February 2022.

PDF
CVPR2022

Learning Non-target Knowledge for Few-shot Semantic Segmentation

Yuanwei Liu, Nian Liu, Qinglong Cao, Xiwen Yao, Junwei Han, Ling Shao

IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022).

PDF Code
TGRS

Scale-Aware Detailed Matching for Few-Shot Aerial Image Semantic Segmentation

Xiwen Yao, Qinglong Cao, Xiaoxu Feng, Gong Cheng, Junwei Han

IEEE Transactions on Geoscience and Remote Sensing (TGRS), October 2021.

PDF Code