Depeng Jin

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning in Urban Road Scenarios

Towards Generalizable LLM Multi-Agent System: Identifying Collective Intelligence Factor in LLM Agent Groups

MobiSim-Bench: A Multi-Perspective Benchmark for Evaluating LLM-Agent-Based Human Mobility Simulation

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems

Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length

A GPU-accelerated Large-scale Simulator for Transportation System Optimization Benchmarking

UrbanDiT: A Foundation Model for Open-World Urban Spatio-Temporal Learning

UrbanPlanBench: A Comprehensive Assessment of Urban Planning Abilities in Large Language Models