Tao Ma  

I am currently a Research Scientist (Topminds "天才少年计划") at Yinwang Ltd (IAS BU), where I lead a group of 10+ researchers and engineers on spatial understanding and intelligence.

Before that, I obtained my Ph.D. degree from Multimedia Laboratory (MMLab) of The Chinese University of Hong Kong, where I was fortunate to be supervised by Prof. Hongsheng Li and Prof. Xiaogang Wang.

My research passion lies in Spatial Understanding and Intelligence, with a recent focus on 3D/4D reconstruction and generative world models towards Physical AI.

Actively looking for self-motivated research interns who are passionate about this direction for long-term collaboration. Please contact me directly if you are interested.

Shenzhen, China

Email  /  Google Scholar  /  Github  /  LinkedIn

News

Education

Working Experience

Publications & Preprints

* indicates equal contribution to the work.

• Multi-modal Multi-task Perception

• ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
  T. Ma*, H. Zhou*, Q. Huang*, X. Yang, J. Guo, B. Zhang, M. Dou, Y. Qiao, B. Shi, H. Li
  Conference on Neural Information Processing Systems (NeurIPS), 2024
  [arXiv / Code]
• DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
  T. Ma, X. Yang, H. Zhou, X. Li, B. Shi, J. Liu, Y. Yang, Z. Liu, L. He, Y. Qiao, Y. Li, H. Li
  International Conference on Computer Vision (ICCV), 2023
  [arXiv / Code / Project Page]
• DetZero++: Offboard 3D Object Detection with Multi-modal Sequential Data
  T. Ma, H. Shang, H. Zhou, X. Yang, X. Li, Y. Li, B. Shi, Y. Qiao, H. Li
• VeloVox: A Low-cost and Accurate 4D Object Detector with Single-frame Point Cloud of Livox LiDAR
  T. Ma*, Z. Zheng*, H. Zhou, X. Cai, X. Yang, Y. Li, B. Shi, H. Li
  IEEE International Conference on Robotics and Automation (ICRA), 2024
  [Paper]
• M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving
  X. Chen, S. Shi, T. Ma, H. Zhou, J. Zhou, S. See, K. Cheung, H. Li
  AAAI Conference on Artificial Intelligence, (AAAI), 2025
• RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection
  Y. Bai, B. Fei, Y. Liu, T. Ma, Y. Hou, B. Shi, Y. Li
  Conference on Neural Information Processing Systems (NeurIPS), 2023
  [Paper]
• LogoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
  X. Li, T. Ma, Y. Hou, B. Shi, Y. Yang, Y. Liu, X. Wu, Q. Chen, Y. Li, Y. Qiao, L. He
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  [arXiv / Code]

• Knowledge-driven Autonomous Driving System

• SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving
  X. Chen, L. Huang, T. Ma, R. Fang, S. Shi, H. Li
  IEEE Conference on Computer Vision and Pattern Recognition , (CVPR), 2025
• DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
  L. Wen*, D. Fu*, X. Li*, X. Cai, T. Ma, P. Cai, M. Dou, B. Shi, L. He, Y. Qiao
  International Conference on Learning Representations (ICLR), 2024
  [arXiv / Code / Project Page]
• Towards Knowledge-driven Autonomous Driving
  X. Li, Y. Bai, P. Cai, L. Wen, D. Fu, B. Zhang, X. Yang, X. Cai, T. Ma, J. Guo, X. Gao, M. Dou, Y. Li, B. Shi, Y. Liu, L. He, Y. Qiao
  arXiv preprint, 2023
  [arXiv]
• On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving
  L. Wen, X. Yang, D. Fu, X. Wang, P. Cai, X. Li, T. Ma, Y. Li, L. Xu, D. Shang, Z. Zhu, S. Sun, Y. Bai, X. Cai, M. Dou, S. Hu, B. Shi, Y. Qiao
  arXiv preprint, 2023
  [arXiv]

• Multi-modal Learning and Generation

• Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging
  Y. Bai, T. Ma, L. Wang, Z. Zhang
  ACM International Conference on Multimedia (ACM MM), 2022
  [arXiv]
• PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
  Y. Li*, T. Ma*, Y. Bai, N. Duan, S. Wei, X. Wang
  Conference on Neural Information Processing Systems (NeurIPS), 2019
  [arXiv / code]
• MOC-GAN: Mixing Objects and Captions to Generate Realistic Images
  T. Ma, Y. Li
  arXiv preprint, 2020
  [arXiv]

• Smart Sensor Sets for Autonomous Driving

• CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes
  T. Ma*, Z. Liu*, G. Yan, Y. Li
  arXiv preprint, 2020
  [arXiv]
• Perception Entropy: A Metric for Multiple Sensors Configuration Evaluation and Design
  T. Ma*, Z. Liu*, Y. Li
  arXiv preprint, 2020
  [arXiv]
• Opencalib: A multi-sensor calibration toolbox for autonomous driving
  G. Yan, Z. Liu, C. Wang, C. Shi, P. Wei, X. Cai, T. Ma, Z. Liu, Z. Zhong, Y. Liu, M. Zhao, Z. Ma, Y. Li
  arXiv preprint, 2022
  [arXiv]

Academic Activities

Teaching