Yuan Gao is currently a Ph.D. student in Tsinghua University and the co-founder of [Aether Reality](https://aether-reality.github.io). His research interests include LLMs, World Models, Computer Vision, and Scientific Machine Learning. He has published over 15 papers at the top international conferences and journals such as ICML, AAAI, KDD, ECCV, etc. He has also served as a reviewer of multiple conferences and journals, including ICLR, NeurIPS, ICML, CVPR, KDD, AAAI, ECCV, etc.

I am actively seeking like-minded collaborators, if you are interested in my work, please feel free to contact me via email: yuangao24@mails.tsinghua.edu.cn.

🔥 News

• 2026.05:  🎉 Two papers were accepted by KDD 2026 (Co-first Author × 1).
• 2026.05:  🎉 One paper was accepted by ICML 2026 (Corresponding Author).
• 2025.11:  🎉 One paper was accepted by AAAI 2026 (First Author).
• 2025.05:  🎉 One paper was accepted by ICML 2025 (First Author).
• 2024.07:  🎉 One paper was accepted by ECCV 2024 (Co-first Author).

📝 Publications

Representative Works († Equal contribution, ‡ Project lead and technical guidance, * Corresponding author)

arXiv 2026

RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models

Hao Wu^†, Yuqi Li^†, Yuan Gao^†, Fan Xu, Fan Zhang, Kun Wang, Penghao Zhao, Qiufeng Wang, Yizhou Zhao, Weiyan Wang, Yingli Tian, Xian Wu, Xiaomeng Huang^*

Paper | Code

ICML 2026

PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting

Hao Wu^†, Fan Xu^†, Yuxu Lu, Penghao Zhao, Fan Zhang, Hao Jia, Yuxuan Liang, Ruijian Gou, Qingsong Wen, Xian Wu^*, Xiaomeng Huang^*, Yuan Gao^*

Paper | Code

AAAI 2026

NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation

Yuan Gao^†, Hao Wu^{† ‡} , Fan Xu, Yanfei Xiang, Ruijian Gou, Ruiqi Shu, Qingsong Wen, Xian Wu^*, Kun Wang^*, Xiaomeng Huang^*

Paper | Code

arXiv 2025

Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias

Hao Wu^†, Yuan Gao^†, Zean Han, Fan Xu, Zhihong Zhu, Qingsong Wen, Xian Wu, Kun Wang^*, Xiaomeng Huang^*

Paper | Code

arXiv 2025

Advanced long-term earth system forecasting

Hao Wu^†, Yuan Gao^†, Ruijian Gou^†, Xian Wu^†, Chuhan Wu^†, Huahui Yi^†, Johannes Brandstetter, Fan Xu, Kun Wang, Penghao Zhao, Hao Jia, Qi Song, Xinliang Liu, Juncai He, Shuhao Cao, Huanshuo Dong, Yanfei Xiang, Fan Zhang, Haixin Wang, Xingjian Shi, Qiufeng Wang, Shuaipeng Li, Ruobing Xie, Feng Tao, Yuxu Lu, Yu Guo, Yuntian Chen, Yuxuan Liang, Qingsong Wen, Wanli Ouyang, Deliang Chen, Niklas Boers, Xiaomeng Huang^*

Paper | Code

ICML 2025

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

Yuan Gao^†, Hao Wu^†, Huanshuo Dong, Fan Xu, Rui Chen, Yibo Yan, Qingsong Wen, Xuming Hu, Kun Wang, Jiahao Wu, Qing Li, Hui Xiong, Xiaomeng Huang^*

Paper | Code

ECCV 2024

OneRestore: A Universal Restoration Framework for Composite Degradation

Yu Guo^†, Yuan Gao^†, Yuxu Lu, Huilin Zhu, Ryan Wen Liu^*, Shengfeng He^*

Project

Paper | Video | Poster | Dataset | Code

IEEE TIM 2023

Let You See in Haze and Sandstorm: Two-in-One Low-visibility Enhancement Network

Yuan Gao^†, Wenyu Xu^†, Yuxu Lu^*

Paper | Code

LLMs, World Models

• Hao Wu^†, Yuqi Li^†, Yuan Gao^†, Fan Xu, Fan Zhang, Kun Wang, Penghao Zhao, Qiufeng Wang, Yizhou Zhao, Weiyan Wang, Yingli Tian, Xian Wu, Xiaomeng Huang^*, RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models, arXiv 2026
• Hao Wu^†, Yongheng Zhang^†, Yuan Gao^†, Fan Xu, Fan Zhang, Ruobing Xie, Ruijian Gou, Yuxuan Liang, Xiaomeng Huang, Xian Wu^*, OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning, arXiv 2026
• Fan Zhang, Haoxuan Li, Shengju Qian^*, Xin Wang, Zheng Lian, Hao Wu, Zhihong Zhu, Yuan Gao, Qiankun Li, Yefeng Zheng, Zhouchen Lin^*, Pheng-Ann Heng, Rethinking facial expression recognition in the era of multimodal large language models: Benchmark, datasets, and beyond, arXiv 2025
• Yu Guo^†, Yuan Gao^†, Yuxu Lu, Huilin Zhu, Ryan Wen Liu^*, Shengfeng He^*, OneRestore: A Universal Restoration Framework for Composite Degradation, ECCV 2024, CCF-B

Scientific Machine Learning

• Hao Wu^†, Yuan Gao^†, Fan Xu^†, Fan Zhang, Qingsong Wen, Kun Wang, Xiaomeng Huang, Xian Wu, Differential-Integral Neural Operator for Long-Term Turbulence Forecasting, KDD 2026
• Huanshuo Dong^†, Hong Wang^†, Hao Wu^†, Zhiwei Zhuang, Xuanze Yang, Ruiqi Shu, Yuan Gao, Xiaomeng Huang^*, An Exterior-Embedding Neural Operator Framework for Preserving Conservation Laws, KDD 2026
• Hao Wu^†, Fan Xu^†, Yuxu Lu, Penghao Zhao, Fan Zhang, Hao Jia, Yuxuan Liang, Ruijian Gou, Qingsong Wen, Xian Wu^*, Xiaomeng Huang^*, Yuan Gao^*, PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting, ICML 2026
• Hao Jia, Penghao Zhao, Hao Wu, Yuan Gao, Yangyu Tao, Bin Cui, Learning from history: a retrieval-augmented framework for spatiotemporal prediction, arXiv 2025
• Hao Wu^†, Yuan Gao^†, Fan Xu^†, Fan Zhang, Guangliang Liu, Yuxuan Liang, Xiaomeng Huang, NeuralOGCM: Differentiable Ocean Modeling with Learnable Physics, arXiv 2025
• Hao Wu^†, Yuan Gao^†, Xingjian Shi, Shuaipeng Li, Fan Xu, Fan Zhang, Zhihong Zhu, Weiyan Wang, Xiao Luo, Kun Wang, Xian Wu^*, Xiaomeng Huang^*, Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models, arXiv 2025
• Yuan Gao^†, Hao Wu^†, Qingsong Wen, Kun Wang, Xian Wu, Xiaomeng Huang^*, VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations, arXiv 2025
• Yuan Gao^†, Hao Wu^{† ‡} , Fan Xu, Yanfei Xiang, Ruijian Gou, Qingsong Wen, Xian Wu^*, Kun Wang^*, Xiaomeng Huang^*, NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation, AAAI 2026, CCF-A
• Hao Wu^†, Yuan Gao^†, Zean Han, Fan Xu, Zhihong Zhu, Qingsong Wen, Xian Wu, Kun Wang^*, Xiaomeng Huang^*, Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias, arXiv 2025
• Hao Wu^†, Yuan Gao^†, Ruijian Gou^†, Xian Wu^†, Chuhan Wu^†, Huahui Yi^†, Johannes Brandstetter, Fan Xu, Kun Wang, Penghao Zhao, Hao Jia, Qi Song, Xinliang Liu, Juncai He, Shuhao Cao, Huanshuo Dong, Yanfei Xiang, Fan Zhang, Haixin Wang, Xingjian Shi, Qiufeng Wang, Shuaipeng Li, Ruobing Xie, Feng Tao, Yuxu Lu, Yu Guo, Yuntian Chen, Yuxuan Liang, Qingsong Wen, Wanli Ouyang, Deliang Chen, Niklas Boers, Xiaomeng Huang^*, Advanced long-term earth system forecasting by learning the small-scale nature, arXiv 2025
• Weiyan Wang, Xingjian Shi, Yuan Gao, Rui Ray Chen, Kun Wang, Fan Xu, Jinbao Xue, Shuaipeng Li, Yangyu Tao, Di Wang, Hao Wu, Xiaomeng Huang^*, BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting, arXiv 2025
• Yuan Gao^†, Hao Wu^†, Huanshuo Dong, Fan Xu, Rui Chen, Yibo Yan, Qingsong Wen, Xuming Hu, Kun Wang, Jiahao Wu, Qing Li, Hui Xiong, Xiaomeng Huang^*, OneForecast: A Universal Framework for Global and Regional Weather Forecasting, ICML 2025, CCF-A

Computer Vision

• Yuxuan Tian, Yu Guo^*, Yuxu Lu, Yuan Gao, Ryan Wen Liu, Towards a physical imaging-driven sparse attention dehazer for Internet of Things-aided Maritime Intelligent Transportation, CEE 2025, JCR Q1
• Lu Li^†, Wenyu Xu^†, Yuan Gao, Yuxu Lu^*, Dong Yang, Ryan Wen Liu, Ran Zhang, Attention-oriented residual block for real-time low-light image enhancement in smart ports, CEE 2024, JCR Q1
• Ryan Wen Liu, Yuxu Lu^*, Yuan Gao, Yu Guo, Wenqi Ren, Fenghua Zhu^*, Fei-Yue Wang, Real-Time Multi-Scene Visibility Enhancement for Promoting Navigational Safety of Vessels Under Complex Weather Conditions, IEEE TITS 2024, JCR Q1, CCF-B
• Wenyu Xu, Dong Yang^*, Yuan Gao, Yuxu Lu^*, Jingming Zhang, Yu Guo, MvKSR: Multi-view Knowledge-guided Scene Recovery for Hazy and Rainy Degradation, IEEE TIM 2024, JCR Q1
• Yuxu Lu, Dong Yang^*, Yuan Gao, Ryan Wen Liu, Jun Liu, Yu Guo, AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration, KBS 2024, JCR Q1
• Jingxiang Qu, Ryan Wen Liu^*, Yuan Gao, Yu Guo, Fenghua Zhu, Fei-Yue Wang, Double Domain Guided Real-time Low-light Image Enhancement for Ultra-high-definition Transportation Surveillance, IEEE TITS 2023, JCR Q1, CCF-B
• Yuan Gao^†, Wenyu Xu^†, Yuxu Lu^*, Let You See in Haze and Sandstorm: Two-in-One Low-Visibility Enhancement Network, IEEE TIM 2023, JCR Q1
• Yu Guo, Yuan Gao, Wen Liu^*, Yuxu Lu, Jingxiang Qu, Shengfeng He, Wenqi Ren, SCANet: Self-paced Semi-curricular Attention Network for Non-homogeneous Image Dehazing, CVPRW 2023
• Jingxiang Qu^†, Yuan Gao^†, Yuxu Lu^*, Wenyu Xu, Ryan Wen Liu^*, Deep learning-driven surveillance quality enhancement for maritime management promotion under low-visibility weathers, OCMA 2023, JCR Q1

🎖 Honors and Awards

• 2025.10 Comprehensive Scholarship of Tsinghua University.
• 2023.09 National Scholarship (Top 1% in China).
• 2022.09 Top Grade Scholarship.
• 2021.09 National Scholarship (Top 1% in China).