Jiayu Ding (丁家钰)

👨‍💻 About Me

I am a first-year Master’s student at the School of Electronics and Computer Engineering (SECE) at Peking University, where I have the privilege of being advised by Prof. Ge Li.

My research operates at the intersection of Large Language Models (LLMs) and spatial-temporal data. My goal is to leverage the structured knowledge and reasoning of LLMs to unlock a deeper, more semantic understanding of complex 3D scenes and dynamic videos. I am excited to contribute to building more capable and perceptive AI systems.

📝 Selected Publications

(*: Equal Contribution, ✉: Corresponding Author)

[1] Polysemous Language Gaussian Splatting via Matching-based Mask Lifting [Paper]
Jiayu Ding, Xinpeng Liu, Zhiyi Pan, Shiqiang Long, Ge Li✉.
The first to elevate the understanding primitive of open-vocabulary 3D Gaussian Splatting from geometric points to semantic objects, achieving state-of-the-art performance across multiple benchmarks.

[2] Open-Vocabulary 3D Instruction Ambiguity Detection [Paper]
Jiayu Ding, Haoran Tang, Ge Li✉.
The first to introduce the task of open-vocabulary instruction ambiguity detection in 3D scene understanding, establishing state-of-the-art results via a novel VLM-based 3D reasoning framework.

[3] A Dual-Layer Complex Network-Based Quantitative Flood Vulnerability Assessment Method of Transportation Systems [Paper]
Jiayu Ding, Yuewei Wang✉, Chaoyue Li. (Land, 2024)
The first to apply a dual-layer complex network model to quantitatively assess the flood vulnerability of transportation systems.

[4] VISTA: Mitigating Semantic Inertia in Video-LLMs via Training-Free Dynamic Chain-of-Thought Routing [Paper]
Hongbo Jin*, Jiayu Ding*, Siyi Xie*, Guibo Luo, Ge Li✉.
The first to identify “Semantic Inertia” in Video-LLMs where visual evidence is suppressed. By proposing VISTA (a training-free dynamic Chain-of-Thought routing framework), it effectively aligns perception with logic, surpassing base models and rivaling larger proprietary models.

📫 Contact

I am always open to discussing research collaborations or new ideas. Please feel free to reach out via email:
jyding25@stu.pku.edu.cn