Publications & Presentations
My research contributions span efficient AI systems, transportation planning, and edge computing.
Journal & Conference Papers
Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Control
Turnau, J., Da, L., Vo, K., Al Rafi, F., Bachiraju, S., Chen, T., & Wei, H. (2025). Reinforcement Learning Journal, 6, 2271–2290.
This work addresses the sim-to-real gap in multi-agent reinforcement learning for traffic signal control, proposing a novel action transformation approach that enables policies trained in simulation to transfer effectively to real-world scenarios.
Preprints & Under Review
Generative AI in Transportation Planning: A Survey
Da, L., Chen, T., Li, Z., Bachiraju, S., Yao, H., Li, L., Dong, Y., Hu, X., Tu, Z., Wang, D., Zhao, Y., Zhou, B., Pendyala, R., Stabler, B., Yang, Y., Zhou, X., & Wei, H. (2025).
A comprehensive survey examining how large language models and generative AI can optimize transportation systems, with a focus on origin-destination matrix estimation and urban planning applications.
Presentations & Posters
Compression of Deep Neural Networks for Edge Devices
Presented research on mixed-precision quantization and model compression techniques for deploying depth-estimation models on NVIDIA Jetson Nano hardware, achieving significant improvements in latency and throughput while maintaining accuracy.