Tao Ma  

I am currently a 3rd-year Ph.D. candidate at Multimedia Laboratory (MMLab) of The Chinese University of Hong Kong, supervised by Prof. Hongsheng Li and Prof. Xiaogang Wang.

My research focuses on scene perception and understanding, and also encompasses end-to-end and knowledge-driven intelligent driving and embodied-AI systems.

Better research, better life. I love cycling sports, please feel free to contact me if you have any questions or similar interests.

Looking for full-time opportunities in industry, please contact me if you are interested in collaboration or recruitment.

SHB 310, CUHK, Hong Kong SAR, 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