👨‍🎓 About Me

I am a PhD candidate at the University of Wisconsin-Madison, advised by Prof. Sikai Chen in Sky-Lab. I am currently a deep learning intern at NVIDIA and previously worked as a research intern at Bosch Research.

My research centers on leveraging foundation models and reinforcement learning to enhance autonomous driving performance. I am currently interested in multimodal large language models and driving world models for safe autonomous driving.

🔥 News

2026.06: ExploreVLA has been accepted by ECCV 2026, see you in Sweden
2026.05: Joining NVIDIA as a deep learning intern for autonomous vehicles
2025.11: Starting a research internship at Bosch Research on Vision-Language-Action (VLA) models
2025.06: I will attend CVPR 2025 to present our latest work Talk2Traffic 🎵
2025.05: Honored to be selected as one of four UW–Madison nominees for the Google PhD Fellowship 🙌
2025.03: We are invited by a leading autonomous driving company to give a talk on our recent project VLM-RL 🚗✨

📝 Selected Publications view all

ECCV

ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving

Zihao Sheng, Xin Ye, Jingru Luo, Sikai Chen, Liu Ren

European Conference on Computer Vision (ECCV) 2026

Webpage PDF Code

CHAIN

SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding

Zihao Sheng, Zilin Huang, Yansong Qu, Jiancong Chen, Yuhao Luo, Yen-Jung Chen, Yue Leng, Sikai Chen

CHAIN, 2026

Webpage PDF Code

TRC

CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models

Zihao Sheng, Zilin Huang, Yansong Qu, Yue Leng, Sruthi Bhavanam, Sikai Chen

Transportation Research Part C: Emerging Technologies, 2026

Webpage PDF Code

CVPRW

Talk2Traffic: Interactive and Editable Traffic Scenario Generation for Autonomous Driving with Multimodal Large Language Model

Zihao Sheng, Zilin Huang, Yansong Qu, Yue Leng, Sikai Chen

CVPR 2025 WDFM-AD

Webpage PDF

TRC

VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving

Zilin Huang*, Zihao Sheng*, Yansong Qu*, Junwei You, Sikai Chen

Transportation Research Part C: Emerging Technologies, 2025

Webpage PDF Code

JICV

Sky-Drive: A Distributed Multi-Agent Simulation Platform for Human-AI Collaborative and Socially-Aware Future Transportation

Zilin Huang*, Zihao Sheng*, Zhengyang Wan*, Yansong Qu, Yuhao Luo, Boyue Wang, Pei Li, Yen-Jung Chen, Jiancong Chen, Keke Long, Jiayi Meng, Yue Leng, Sikai Chen

Journal of Intelligent and Connected Vehicles, 2025

Webpage PDF Code

🎖 Honors and Awards

2025 Google PhD Fellowship Nominee, University of Wisconsin–Madison (Among 4 nominees university-wide)
2025 NVIDIA Academic Grant Program Award Winner (20K A100 GPU-Hours + 2x RTX PRO 6000 Blackwell GPUs)
2024, 2025 ESI Highly Cited Paper (Top 1% in Engineering)
2023 Student Research Grants Competition (SRGC) Award, University of Wisconsin–Madison
2023 Best Presentation Award, 3rd Annual Conference of Next-Generation Transportation Systems
2022 Best Dissertation Award (Top 3%), Shanghai Association of Automation (SAA)
2022 Outstanding Master’s Graduate Award, Shanghai Jiao Tong University

📖 Educations

2023.01 – Present, Ph.D., Univerity of Wisconsin-Madison, WI, USA
2019.09 – 2022.03, M.Eng., Shanghai Jiao Tong University, China
2015.09 – 2019.06, B.Eng., Xi’an Jiaotong University, China

💡 Services

Reviewer for Conferences (ICCV, AAAI, ITSC, SMC, TRB) and Journals (RA-L, TR-C, T-ITS, T-VT, T-IV, T-MC, AAP)
Spring 2026, TA, CEE 370 Transportation Engineering, University of Wisconsin-Madison
Spring 2025, TA, CEE 370 Transportation Engineering, University of Wisconsin-Madison
Spring 2024, TA, CEE 370 Transportation Engineering, University of Wisconsin-Madison
Fall 2020, TA, Digital Signal Processing, Shanghai Jiao Tong University