Lingdong Kong
I am a Ph.D. candidate in the Department of Computer Science at the National University of Singapore, advised by Prof. Wei Tsang Ooi, Prof. Benoit Cottereau, and Dr. Lai Xing Ng. I also collaborate closely with Prof. Ziwei Liu from Nanyang Technological University, Singapore.
My research focuses on developing 3D scene understanding systems that are robust, scalable, and generalizable in real-world conditions.
I have been fortunate to collaborate with Apple Machine Learning Research, NVIDIA Research, ByteDance Seed, ByteDance AI Lab, OpenMMLab, MMLab@NTU, and Motional.
I am the recipient of the National Scholarship (Ministry of Education, 2019), NUS Research Achievement Award (NUS Computing, 2023), and Dean's Graduate Research Excellence Award (NUS Computing, 2024),
🦁 I am open to discussion and collaboration in 3D scene perception, generation, and understanding. If you find our research backgrounds a potential match, feel free to email me.
News
- [02/2025] - We are hosting The RoboSense Challenge.
- [02/2025] - DynamicCity was selected as a spotlight at ICLR 2025.
- [01/2025] - Calib3D was selected for oral presentation at WACV 2025.
- [09/2024] - Place3D was selected as a spotlight at NeurIPS 2024.
- [04/2024] - OpenESS was selected as a highlight at CVPR 2024.
- [11/2023] - We are hosting The RoboDrive Challenge at ICRA 2024.
- [09/2023] - Seal was selected as a spotlight at NeurIPS 2023.
- [03/2023] - LaserMix was selected as a highlight at CVPR 2023.
Industrial Experience
|
NVIDIA Research |
|
Shanghai AI Laboratory |
|
ByteDance AI Lab |
|
OpenMMLab |
|
Motional |
Recent Publications
* equal contributions ‡ project lead § corresponding author
|
DynamicCity: Large-Scale Occupancy Generation from Dynamic Scenes  Spotlight (5.1% = 580/11372)
|
|
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding Oral Presentation
|
|
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving |
|
LiMoE: Mixture of LiDAR Representation Learners from AutomotiveScenes
arXiv, 2025
|
|
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
arXiv, 2025
|
|
FlexEvent: Event Camera Object Detection at Arbitrary Frequencies
arXiv, 2025
|
|
GEAL: Generalizable 3D Object Affordance Learning with Cross-Modal Consistency
arXiv, 2025
|
|
SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
arXiv, 2025
|
|
OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies
arXiv, 2025
|
|
LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving
arXiv, 2025
|
|
Is Your LiDAR Placement Optimized for 3D Scene Understanding? Spotlight (2.5% = 388/15671)
|
|
Is Your HD Map Constructor Reliable under Sensor Corruptions? |
|
4D Contrastive Superflows are Dense 3D Representation Learners |
|
Learning to Adapt SAM for Segmenting Cross-Domain Point Clouds |
|
OpenESS: Event-Based Semantic Scene Understanding with Open Vocabularies Highlight (2.8% = 324/11532)
|
|
Multi-Space Alignments Towards Universal LiDAR Segmentation |
|
Unified 3D and 4D Panoptic Segmentation via Dynamic Shifting Networks |
|
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving |
|
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions |
|
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models Spotlight (3.0% = 378/12343)
|
|
Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective |
|
Towards Label-Free Scene Understanding by Vision Foundation Models |
|
Robo3D: Towards Robust and Reliable 3D Perception against Corruptions |
|
Rethinking Range View Representation for LiDAR Segmentation |
|
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase |
|
LaserMix for Semi-Supervised LiDAR Semantic Segmentation Highlight (2.5% = 235/9155)
|
|
CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP |
|
ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation |
|
Benchmarking 3D Robustness to Common Corruptions and Sensor Failure Best Workshop Paper Award
|
Tech Reports
|
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
Technical Report, 2024
|
|
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
Technical Report, 2023
|
Workshop Organizers
Venue: Yokohama, Japan
Academic Services
Conference Reviewer
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- IEEE/CVF International Conference on Computer Vision (ICCV)
- European Conference on Computer Vision (ECCV)
- Conference on Neural Information Processing Systems (NeurIPS)
- International Conference on Learning Representations (ICLR)
- International Conference on Machine Learning (ICML)
- IEEE International Conference on Robotics and Automation (ICRA)
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Journal Reviewer
- International Journal of Computer Vision (IJCV)
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
- IEEE Transactions on Intelligent Vehicles (TIV)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- IEEE Transactions on Multimedia (TMM)
- IEEE Transactions on Knowledge and Data Engineering (TKDE)
- IEEE Robotics and Automation Letters (RA-L)
- ISPRS Journal of Photogrammetry and Remote Sensing (P&RS)