Jingli Lin portrait
JL
Embodied AI · 3D Vision · Spatial Intelligence

Jingli Lin

Ph.D. student in Artificial Intelligence at Shanghai Jiao Tong University. My research focuses on embodied AI, 3D perception, spatial reasoning, and world models.

About

Research profile

My research interests lie in Embodied AI, 3D Vision, Spatial Reasoning, and World Models. I study 3D scene understanding and spatial perception, construct and evaluate spatial reasoning benchmarks, and explore the design and training of spatial intelligence foundation models. My goal is to enhance the spatial cognition, reasoning, and decision-making capabilities of multimodal large models in complex 3D environments.

Embodied AI 3D Perception Spatial Reasoning World Models Multimodal Learning

Education

Academic background

Shanghai Jiao Tong University

Sept. 2025 -- Present
Ph.D. in Artificial Intelligence

Shanghai Jiao Tong University

Sept. 2021 -- June 2025
B.E. in Artificial Intelligence, Honor Class

Experience

Research experience

InternRobotics, Shanghai AI Laboratory

Nov. 2024 -- Present
Research Intern · Advisor: Jiangmiao Pang
  • Research 3D perception and the construction and evaluation of spatial reasoning benchmarks.
  • Explore the design and training of spatial intelligence foundation models.

CILAB, Shanghai Jiao Tong University

July 2022 -- Feb. 2023
Research Assistant Intern · Advisor: Assoc. Prof. Guanjie Zheng
  • Researched urban traffic prediction and algorithmic optimization for urban traffic flow.

Publications

* Equal contribution
MMSI-Video-Bench teaser
MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence
Jingli Lin*, Runsen Xu*, Shaohao Zhu, Sihan Yang, Peizhou Cao, Yunlong Ran, Miao Hu, Chenming Zhu, Yiman Xie, Yilin Long, Wenbo Hu, Dahua Lin, Tai Wang, Jiangmiao Pang
arXiv:2512.10863
PaperCodeProject
OST-Bench teaser
OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
Jingli Lin*, Chenming Zhu*, Runsen Xu, Xiaohan Mao, Xihui Liu, Tai Wang, Jiangmiao Pang
NeurIPS 2025
PaperCodeProject
G2VLM teaser
G²VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
Wenbo Hu*, Jingli Lin*, Yilin Long*, Yunlong Ran, Lihan Jiang, Yifan Wang, Chenming Zhu, Runsen Xu, Tai Wang, Jiangmiao Pang
CVPR 2026
PaperCodeProject
MMScan teaser
MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
Ruiyuan Lyu*, Jingli Lin*, Tai Wang*, Shuai Yang*, Xiaohan Mao, Yilun Chen, Runsen Xu, Haifeng Huang, Chenming Zhu, Dahua Lin, Jiangmiao Pang
NeurIPS 2024
PaperCode
MMSI-Bench teaser
MMSI-bench: A Benchmark for Multi-image Spatial Intelligence
Sihan Yang, Runsen Xu, Yiman Xie, Sizhe Yang, Mo Li, Jingli Lin, Chenming Zhu, Xiaochen Chen, Haodong Duan, Xiangyu Yue, Dahua Lin, Tai Wang, Jiangmiao Pang
ICLR 2026
PaperCodeProject
G2TAM teaser
G2TAM: Geometry Grounded Track Anything Model
Chenming Zhu, Peizhou Cao, Jingli Lin, Wenbo Hu, Yunlong Ran, Tai Wang, Jiangmiao Pang, Xihui Liu
ICML 2026
PaperCodeProject
InternScenes teaser
Internscenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
Weipeng Zhong*, Peizhou Cao*, Yichen Jin, Luo Li, Wenzhe Cai, Jingli Lin, Hanqing Wang, Zhaoyang Lyu, Tai Wang, Xudong Xu, Bo Dai, Jiangmiao Pang
NeurIPS 2025
PaperCodeProject
Auto-Pairing teaser
Auto-Pairing Positives through Implicit Relation Circulation for Discriminative Self-Learning
Bo Pang, Zhenyu Wei, Jingli Lin, Cewu Lu
IEEE TPAMI
PaperCode
Traffic signal control teaser
Big-data Empowered Traffic Signal Control Could Reduce Urban Carbon Emission
Kan Wu, Jianrong Ding, Jingli Lin, Guanjie Zheng, Yi Sun, Jie Fang, Tu Xu, Yongdong Zhu, Baojing Gu
Nature Communications, 2025
Paper

Honors & Awards

2021–2024

Zhiyuan Scholarship

Shanghai Jiao Tong University

2022

Guozhi Scholarship

Shanghai Jiao Tong University

2023

B-Class Scholarship

Shanghai Jiao Tong University

2022

Second Prize (Provincial)

Contemporary Undergraduate Mathematical Contest in Modeling