PhD Researcher · OpenDriveLab · Fudan University

Tianyu Li 李天羽

Pushing boundaries of _

View Research Get in Touch

scroll

About

I am a PhD student at Fudan University and Shanghai Innovation Institute, conducting research at OpenDriveLab under the supervision of Prof. Hongyang Li.

My research focuses on autonomous driving, Physical AI, end-to-end AD systems, 3D reconstruction, and generative models. I'm passionate about developing Physical AI systems that can perceive, understand, and interact with the physical world.

Autonomous Driving Physical AI

Publications

CVPR'26 arxiv:2511.23369

SimScale: Learning to Drive via Real-World Simulation at Scale

Haochen Tian, Tianyu Li, Haochen Liu, Jiazhi Yang, et al.

Paper → Code

CVPR'26 arxiv:2601.12901

PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning

Hongchen Li, Tianyu Li, Jiazhi Yang, Haochen Tian, et al.

Paper →

TPAMI'26 arxiv:2506.09800

Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving

Haochen Liu, Tianyu Li, Haohan Yang, Li Chen, et al.

Paper →

arXiv arxiv:2512.07661

OMEGA: Optimization-Guided Diffusion for Interactive Scene Generation

Shihao Li, Naisheng Ye, Tianyu Li, Kashyap Chitta, et al.

Paper →

arXiv arxiv:2601.05611

LatentVLA: Efficient Vision-Language Models for Autonomous Driving via Latent Action Prediction

Chengen Xie, Bin Sun, Tianyu Li, et al.

Paper →

CoRL'25 arxiv:2506.04218

Pseudo-Simulation for Autonomous Driving

Wei Cao*, Marcel Hallgarten*, Tianyu Li*, et al.

Paper → Code

arXiv arxiv:2503.12552

MTGS: Multi-Traversal Gaussian Splatting

Tianyu Li, Yihang Qiu, Zhenhua Wu, et al.

Paper → Code

NeurIPS'24 arxiv:2406.15349

NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

Daniel Dauner, Marcel Hallgarten, Tianyu Li, et al.

Paper → Code

NeurIPS'25 arxiv:2505.17771

TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving

Yanping Fu, Xinyuan Liu, Tianyu Li, et al.

Paper → Code

ICLR'24 arxiv:2312.16108

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

Tianyu Li, Peijing Jia, Bangjun Wang, et al.

Paper → Code

NeurIPS'23 arxiv:2304.10440

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

Huijie Wang*, Tianyu Li*, Yang Li*, et al.

Paper → Code

SCIS'26 arxiv:2304.05277

Graph-based Topology Reasoning for Driving Scenes

Tianyu Li, Li Chen, Huijie Wang, et al.

Paper → Code

PRCV'24 arxiv:2303.10340

3D Data Augmentation for Driving Scenes on Camera

Wenwen Tong*, Jiangwei Xie*, Tianyu Li*, et al.

Paper →

ICCV'25 arxiv:2504.10485

Decoupled Diffusion Sparks Adaptive Scene Generation

Yunsong Zhou, Naisheng Ye, William Ljungbergh, Tianyu Li, et al.

Paper → Code

CVPR'24 Highlight arxiv:2403.09630

Generalized Predictive Model for Autonomous Driving

Jiazhi Yang, Shenyuan Gao, Yihang Qiu, Li Chen, Tianyu Li, et al.

Paper → Code

ECCV'24 arxiv:2312.17118

Fully Sparse 3D Occupancy Prediction

Haisong Liu, Yang Chen, Haiguang Wang, Zetong Yang, Tianyu Li, et al.

Paper → Code

ECCV'24 arxiv:2403.04593

Embodied Understanding of Driving Scenarios

Yunsong Zhou, Linyan Huang, Qingwen Bu, Jia Zeng, Tianyu Li, et al.

Paper → Code

Academic Service

Reviewer

Journals

Nature Science Robotics IEEE TPAMI

Conferences

CVPRICCVECCV NeurIPSICMLICLRAAAI

Organizer

2025

Autonomous Grand Challenge @ ICCV & CVPR 2025

2024

Autonomous Grand Challenge @ CVPR'24

Get in Touch

Open to research collaborations, discussions on autonomous driving and Physical AI, or any exciting opportunities.

Email sephy.fine@gmail.com

X / Twitter @sephy_li

LinkedIn sephy-li