About Me

Hi! I am a second-year Ph.D. student of MMLab, The Chinese University of Hong Kong, supervised by Prof. Dahua Lin. Currently, I am a remote visiting student at Shanghai AI Laboratory, working with Jiangmiao Pang. Prior to this, I received my Bachelor’s degree in Computer Science and Technology from Chu Kochen Honors College (Pursuit Science Class) at Zhejiang University in 2022. In ZJU, I was fortunate to be supervsied by Prof. Guofeng Zhang, at the State Key Lab of CAD&CG.

My reserach interest lies in 3D understanding for robotics (spatial AI). My long-term goal is to develop an intellectual model capable of universally perceiving and reasoning about our 3D physical world—primarily through visual information and various multi-modal data—that can be deployed on robots or wearable devices (like AR glasses). This pursuit aims to augment human intelligence and to benefit society at large. Achieving this goal involves overcoming three core challenges:

  1. Output: defining what perceptions are essential for the intelligent agent.
  2. Representation: establishing a viable world (scene) representation.
  3. Data: addressing the difficulty in acquiring necessary training data.

I am generally interested in research that seeks solutions to these problems. Currently, my exploration focuses on leveraging the successes of foundation models in both vision and language, as well as the advancements in generative modeling to address these issues. If you share my interests, have articles to recommend that are helpful, or simply have any queries, please do not hesitate to contact me. :)

News

  • [Sep. 2023] Our HC-Net is accepted by NeurIPS 2023! 🎉
  • [Aug. 2023] We release PointLLM, a multi-modal large language model capable of understanding point clouds! Try our demo here. 🤗
  • [Aug. 2023] We release HC-Net, a SOTA fine-grained cross-view geo-localization model! Demo here. 📊
  • [Mar. 2023] Our paper on MV-JAR, a LiDAR-based self-supervised pre-training method along with a new data-efficient benchmark, has been accepted by CVPR 2023. 🎉
  • [Jun. 2022] Graduated from Zhejiang University. Forever cherishing the memories from ZJU. 🎓
  • [Apr. 2022] Honored to receive the Hong Kong PhD Fellowship (HKPFS) and the CUHK Vice-Chancellor’s PhD Scholarship. Deeply grateful for the recognition! 🏆

Education

cuhk
 The Chinese University of Hong Kong (CUHK)
  August 2022 - June 2026 (Expected)
  Ph.D. in Information Engineering
zju
 Zhejiang University (ZJU)
  September 2018 - June 2022
  B.Eng. in Computer Science and Technology

Publications

3D Perception and Understanding
PointLLM
PointLLM: Empowering Large Language Models to Understand Point Clouds
Runsen Xu, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang#, Dahua Lin
arXiv Preprint, 2023
[Paper] [Code] [Project] [Demo] [Cite]
Self-Supervised 3D Representation Learning
MV-JAR
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
Runsen Xu, Tai Wang, Wenwei Zhang, Runjian Chen, Jinkun Cao, Jiangmiao Pang#, Dahua Lin
Computer Vision and Pattern Recognition, CVPR 2023
[Paper] [Code] [Video] [Slides] [Cite]
CO^3
COˆ3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
Runjian Chen, Yao Mu, Runsen Xu, Wenqi Shao, Chenhan Jiang, Hang Xu, Zhenguo Li, Ping Luo
International Conference on Learning Representations, ICLR 2023
[Paper] [Code] [Cite]
Robot Localization and Navigation
HC-Net
Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator
Xiaolong Wang, Runsen Xu, Zuofan Cui, Zeyu Wan, Yu Zhang
Neural Information Processing Systems, NeurIPS 2023
[Paper] [Code] [Demo] [Cite]
RNIN-VIO
RNIN-VIO: Robust Neural Inertial Navigation Aided Visual-Inertial Odometry in Challenging Scenes
Danpeng Chen, Nan Wang, Runsen Xu, Weijian Xie, Hujun Bao, Guofeng Zhang
International Symposium on Mixed and Augmented Reality, ISMAR 2021, Oral Presentation
[Paper] [Code] [Project] [Cite]

Research Experiences

OpenRobotLab, Shanghai AI Laboratory, Mar. 2023 - Present

  • Remote visiting student mentored by Jiangmiao Pang.
  • Worked on 3D vision and language, multi-modal large language models (LLMs).

Shanghai AI Laboratory, Nov. 2021 - July 2022

  • Research intern mentored by Jiangmiao Pang.
  • Worked on self-supervised 3D representation learning.

3D Vision Group, CAD&CG State Key Lab, Zhejiang University, Mar. 2020 - Oct. 2021

  • Research assistant advised by Prof. Guofeng Zhang.
  • Worked on indoor AR navigation, indoor navigation solutions for individuals with visual impairments, and optical flow estimation.

Mobile SLAM, SenseTime Group Ltd., Mar. 2021 - June 2021

  • Research intern
  • Worked on neural inertial navigation with IMU data.

Selected Awards

  • Hong Kong PhD Fellowship (most prestigious scholarship for Ph.D. studies in Hong Kong), 2022
  • CUHK Vice-Chancellor’s PhD Scholarship, 2022
  • Outstanding Graduates of Zhejiang University, 2022
  • Outstanding Undergraduate Thesis of College of Computer Science and Technology, Zhejiang University, 2022
  • National Scholarship (highest honor nationwide for Chinese undergraduates), 2019

Teaching

  • IERG4998: Final Year Project, Spring 2023
  • IERG4998: Final Year Project, Fall 2022