Projects: OpenTI, ICLR'26a, EACL'26a (Instructional Agents), EACL'26b, EACL'26c, ACL'25a, ACL'25b, KDD'25a, KDD'25b, IJCAI'25 (DeepShade), SDM'25a, SDM'25b, KDD'26a (ShadeBench), ICML'26a, ICML'26b
Generative AI expresses the possibility of human-like AI. We investigate its potential and pitfalls.
Papers: KDD'26a (ShadeBench) ECML-PKDD'24a, PADS'23, ERA'23, KDD'22, AAAI'21, ICDE'21, ECML-PKDD'20
Realistic simulators are a step closer towards policymaking for the real world. We investigate how to build realistic simulators from real-world data.
Project websites: Terminal Simulation, CityFlowER, Honor of Kings (王者荣耀), LibSignal, CityFlow, Epidemic, Product Allocator
Simulators are the foundation of reinforcement learning. We built a bunch of simulators for various applications, including MOBA Games, transportation, epidemics, and product allocation.
Papers: ACL'26a, ACL'26b, ACL'26c, EACL'26b, EACL'26c, SIGKDD Explorations'25, COLM'25, KDD'25a, KDD'25c, ICML'25a, ICML'25b, AAAI'24a, AAAI'24c, ICDM'23, CDC'23a, CIKM'23, KDD'23, IJCAI'23, ERA'23, AAAI'23, IAAI'22, IJCAI'21a, IJCAI'21b, USENIX Security'21 (Adversarial Policies)
The project investigates different aspects of trustworthy deep learning, including robust modeling for deep learning models with physics, reinforcement learning with offline data, and adversarial policy training.
Papers: Survey (Arxiv), Survey(KDD Explorations), AAAI'24a, CDC'23a, CDC'23b, CASE'23, IJCAI'23, AAAI'23, AAAI'20, KDD'19, CIKM'19a, CIKM'19b, KDD'18
The project systematically investigates "smart" traffic light control systems using deep reinforcement learning and evaluate its effectiveness on both synthetic and real-world traffic data.
