Hello, I am Songyang Gao, a first-year MPhil student in Artificial Intelligence at The Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Hui Xiong (IEEE, ACM, AAAI, AAAS Fellow). I received my B.Eng. in Artificial Intelligence from Nanchang University in 2025.

My current research interests focus on Agentic Systems and Streaming Systems. I am designing Agentic Systems for Large-Scale Data Tasks, including building a Streaming Agent Benchmark for Real-Time Data Pipelines. In addition, I am also interested in applications of Agentic Systems, such as intelligent agents for scientific research and computer use agents.

Previously, I worked on generative AI algorithms and their applications in computational imaging and intelligent medical imaging at LIVE Lab, Nanchang University, advised by Prof. Qiegen Liu and Wenbo Wan.

Click here to visit my CV. Click here to read about my personal growth and life story. If you have any questions, feel free to drop me an email!

I am actively looking for Fall 2027 Ph.D. programs. Please feel free to contact me!

Email: sgao068@connect.hkust-gz.edu.cn

NEWS

Paper submitted to KDD 2026, February, 2026

Our paper “SAB: A Streaming Agent Benchmark for Real-Time Data Pipelines” (Y. Xia*, S. Gao*, H. Xiong, *equal contribution) has been submitted to KDD 2026.

Participated in Singtel PIE Program, Singapore, December, 2025

I had been selected to participate in the Singtel Pio-Innovation-Enterprise (PIE) Program in Singapore (Dec 7-14, 2025) as a group leader. Our team designed and proposed SmartShield, a multi-modal scam detection and prevention system via rule-LLM synergy, combining field research in Singapore with AI-driven solutions for real-world fraud prevention.

Started MPhil at HKUST(GZ), September, 2025

I officially started my MPhil study in Artificial Intelligence at HKUST(GZ), advised by Prof. Hui Xiong.

Graduated from Nanchang University, June, 2025

I Graduated from Nanchang University and completed my bachelor thesis with Excellent.

Won the Baosteel Scholarship Special Prize (only 15 winners nationwide), November, 2024

Click here to read the official report.

Paper accepted by the Optics Express, August, 2024

Our paper “DMEDH: Diffusion Model-boosted Multiplane Extrapolation for Digital Holographic Reconstruction” is accepted by the Optics Express.

Won the Best Poster Award of the 6th Symposium on Computational Imaging Technology and Applications (2024), May 19, 2024

Our paper “DMEDH: Diffusion Model-boosted Multiplane Extrapolation for Digital Holographic Reconstruction”(扩散模型增强的多平面外推数字全息图像重建 in Chinese) was accepted and awarded the best poster award by the 6th Symposium on Computational Imaging Technology and Applications (2024)

Won the Outstanding Academic Correspondent in CAAI Transactions on Intelligence Technology, May 14, 2024

I passed the screening and entered the editorial department of the CAAI Transactions on Intelligence Technology for internship on January 1, 2024. I completed more than five months of internship and was named an outstanding academic correspondent.

Paper accepted by the Photonics, April, 2024

Our paper “HoloDiffusion: Sparse Digital Holographic Reconstruction via Diffusion Modeling” is accepted by the Photonics.

Start internship at the winter camp of Institute for AI Industry Research, Tsinghua University, January 15, 2024

I am doing my research at THU under the supervision of Yan Wang.

Our research topics are weather scene generation and editing based on stable diffusion.I completed the winter camp on March 15, 2024.

Paper accepted by the Applied Physics Letters, January, 2024

Our paper “Imaging through scattering media via generative diffusion model” is accepted by the Applied Physics Letters.

Won Huawei “Smart Base” Scholarship, December, 2023

I won the Huawei “Smart Base” Scholarship (ratio: 0.3%) and was named the Ministry of Education-Huawei “Smart Base” Future Star.

Paper accepted by the Frontiers in Neuroscience, April, 2023

Our paper “ARA-Net: An Attention-Aware Retinal Atrophy Segmentation Network Coping With Fundus Images” is accepted by the Frontiers in Neuroscience.