Depeng Jin

Full Professor, EE, Tsinghua University, Tsinghua University

Joined

July 2019

Names

Depeng Jin

Emails

****@tsinghua.edu.cn (Confirmed)

Personal Links

DBLP

Career & Education History

Full Professor

EE, Tsinghua University, Tsinghua University (tsinghua.edu.cn)

2012 – Present

Advisors, Relations & Conflicts

Coauthor

Jian Yuan

Present

Coauthor

Yong Li

2007 – Present

Expertise

Artificial Intelligence

2016 – Present

Urban Science

2016 – Present

Publications

MobiSim-Bench: A Multi-Perspective Benchmark for Evaluating LLM-Agent-Based Human Mobility Simulation
Jun Zhang, Yuwei Yan, Zhiheng Zheng, Boyuan Sun, Jinghua Piao, Depeng Jin, Pan Hui, Qingmin Liao, Yong Li
- Submitted to ICLR 2026
- Readers: Everyone
RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning in Urban Road Scenarios
Jun Zhang, Jie Feng, Long Chen, Junhui Wang, Zhicheng Liu, Depeng Jin, Yong Li
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Towards Generalizable LLM Multi-Agent System: Identifying Collective Intelligence Factor in LLM Agent Groups
Zhilun Zhou, Zihan Liu, Jiahe Liu, Yihan Wang, Qingyu Shao, Fengli Xu, Depeng Jin, Yong Li
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Diffusion Transformers as Open-World Spatiotemporal Foundation Models
Yuan Yuan, Chonghua Han, Jingtao Ding, Guozhen Zhang, Depeng Jin, Yong Li
- NeurIPS 2025 poster
- Readers: Everyone
Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems
Hongyuan Su, Yu Zheng, Yuan Yuan, Yuming Lin, Depeng Jin, Yong Li
- ICML 2025 poster
- Readers: Everyone
UrbanPlanBench: A Comprehensive Assessment of Urban Planning Abilities in Large Language Models
Yu Zheng, Longyi Liu, Yuming Lin, Jie Feng, Guozhen Zhang, Depeng Jin, Yong Li
- Submitted to ICLR 2025
- Readers: Everyone
A GPU-accelerated Large-scale Simulator for Transportation System Optimization Benchmarking
Jun Zhang, Wenxuan Ao, Junbo Yan, Depeng Jin, Yong Li
- Submitted to ICLR 2025
- Readers: Everyone
Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length
Zihan Yu, Jingtao Ding, Yong Li, Depeng Jin
- ICLR 2025 Poster
- Readers: Everyone
UrbanDiT: A Foundation Model for Open-World Urban Spatio-Temporal Learning
Yuan Yuan, Chonghua Han, Jingtao Ding, Guozhen Zhang, Depeng Jin, Yong Li
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Adjustable Quantile-Guided Diffusion Policy for Diverse Behavior Generation in Offline RL
Wenzhen Huang, Tong Li, Junge Zhang, Depeng Jin, Yong Li
- Submitted to ICLR 2024
- Readers: Everyone

View all 22 publications

Co-Authors

View all 63 co-authors