Jiayu Ding

Hi! I am Jiayu Ding (Chinese name: 丁家钰), currently studying at the School of Electronics and Computer Engineering (SECE), Peking University. My research operates at the intersection of Large Language Models (LLMs) and spatial-temporal data, aiming to leverage the structured knowledge and reasoning of LLMs to unlock a deeper, more semantic understanding of complex 3D scenes and dynamic videos.

Feel free to contact me by email if you are interested in discussing or collaborating with me.

Detailed Profile (详细个人介绍)

Hi! I am Jiayu Ding (Chinese name: 丁家钰), currently studying at the School of Electronics and Computer Engineering (SECE), Peking University.

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. Recently, my work has been accepted to ACM MM 2026, ECCV 2026, CVPR 2026, and ICML 2026.

Hi！我是丁家钰 (English name: Jiayu Ding)，北京大学电子与计算机工程学院（SECE）在读研究生。

我的研究聚焦于大语言模型（LLMs）与时空数据的交叉方向，希望借助大模型的结构化知识与推理能力，实现对复杂三维场景与动态视频更深层、更具语义的理解，从而构建更强大、更具感知力的 AI 系统。近期工作被 ACM MM 2026、ECCV 2026、CVPR 2026、ICML 2026 等顶级会议接收。

News

07/2026 🎉 Two papers (CausalSplat, R4DGS) are accepted to ACM MM 2026 !
06/2026 🎉 One paper (ZeroSplat) is accepted to ECCV 2026 !
04/2026 🎉 One paper (3DSAV) is accepted to ICML 2026 !
02/2026 🎉 One paper (ExtrinSplat) is accepted to CVPR 2026 !

Education

Present

Peking University (PKU)

School of Electronics and Computer Engineering (SECE)

Currently studying. Research: LLMs × spatial-temporal understanding (3D scenes & videos).

Publications

* Equal contribution. ✉ Corresponding author.

CausalSplat: Towards Comprehensive Hierarchical Reasoning in 3D Gaussian Splatting

Jiayu Ding*, Meilu Song*, Yun Chen*, Wei Gao, Ge Li✉

ACM MM 2026

arXiv Project Page
ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting

Jiayu Ding*, Meilu Song*, Xiaoyi Zhang, Hongbo Jin, Yichen Jin, Xiangtian Si✉

ECCV 2026

arXiv Project Page
ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting

Jiayu Ding, Xinpeng Liu, Zhiyi Pan, Shiqiang Long, Ge Li✉

CVPR 2026

Paper arXiv Demo
3D Scene Assertion Verification

Jun Lin*, Jiayu Ding*✉, Xiangtian Si, Xitong Cao, Lixin Hong, Zhang Chen, Chenxi Lv, Wenqian Wang

ICML 2026

Paper Benchmark
R4DGS: Referring Segmentation in 4D Gaussian Splatting

Bangpu Chen, Yaxuan Li, Shirui Peng, Xiangtian Si, Liuxin Chu, Xitong Cao, Hongbo Jin, Jiayu Ding✉

ACM MM 2026

Paper Project Page Code
Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models

Jiayu Ding*, Zhuodong Liu*, Lei Zhang*, Manyu Xiong, Hongbo Jin, Haoran Tang, Hongbo Zhang, Changen Zhu, Wenbo Xing✉

Preprint 2026

arXiv Project Page Code
3D Instruction Ambiguity Detection

Jiayu Ding, Haoran Tang, Hongbo Jin, Wei Gao, Ge Li✉

Preprint 2026

arXiv Project Page Code
LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue

Chaoyue Li, Yongxue Xu, Jie Feng, Jiayu Ding✉

Preprint 2026

arXiv Project Page Code

Open Source

CCFA Skills – GitHub Repository

A skill family for shaping the research storyline of CCF-A papers.

CCFA Skills is a family of 17 AI-agent skills covering the full research pipeline, from idea evaluation to paper submission. It works with Codex, Claude Code, Cursor, and Gemini CLI and is released under the MIT License.

Contact

Research: I welcome talented researchers to collaborate on meaningful, impactful work at the intersection of LLMs and spatial-temporal understanding.

Entrepreneurship: We aim to train a general-purpose 4D understanding foundation model, and further drive industrial adoption in related domains such as Vision-Language-Action (VLA), Vision-Language Navigation (VLN), and other embodied AI applications.

📧 Email: jyding25@stu.pku.edu.cn