Runjian Chen

University of Hong Kong — Hong Kong

Computer Science · Physical Sciences

7h-index458citations33works1.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(8), Robotics and Sensor-Based Localization(8), Advanced Image and Video Retrieval Techniques(5), Advanced Graph Neural Networks(5), Domain Adaptation and Few-Shot Learning(5)

Publications33 total

Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
arXiv (Cornell University)·2025Open Access
JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data
2025· 1 cited
JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data
arXiv (Cornell University)·2025Open Access
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
arXiv (Cornell University)·2024Open Access
TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
arXiv (Cornell University)·2024Open Access
MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
arXiv (Cornell University)·2024· 6 citedOpen Access
Position: Towards Implicit Prompt For Text-To-Image Models
arXiv (Cornell University)·2024Open Access
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
arXiv (Cornell University)·2024· 3 citedOpen Access
CurriculumLoc: Enhancing Cross-Domain Geolocalization Through Multistage Refinement
IEEE Transactions on Geoscience and Remote Sensing·2024· 2 cited
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
arXiv (Cornell University)·2023Open Access
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations
arXiv (Cornell University)·2023· 2 citedOpen Access
CycleMLP: A MLP-Like Architecture for Dense Visual Predictions
IEEE Transactions on Pattern Analysis and Machine Intelligence·2023· 99 cited
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
2023· 20 cited
Failure-aware Policy Learning for Self-assessable Robotics Tasks
2023· 2 cited
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
arXiv (Cornell University)·2023· 1 citedOpen Access
Failure-aware Policy Learning for Self-assessable Robotics Tasks
arXiv (Cornell University)·2023Open Access
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
arXiv (Cornell University)·2022· 2 citedOpen Access
CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
arXiv (Cornell University)·2022· 3 citedOpen Access
RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 106 cited
page 1 of 2Next →

Frequent Co-authors

Ping Luo(8), Wenqi Shao(8), Rong Xiong(7), Yue Wang(6), Haoyan Xu(5), Ziheng Duan(5), Jie Feng(5), Yu Qiao(5), Shoufa Chen(4), Huan Yin(4), Ping Luo(4), Chongjian Ge(3), Runsen Xu(3), Yanmei Jiao(3), Gamini Dissanayake(3), Yunsheng Bai(3), Yao Mu(3), Bo Zhang(3), Zhouxia Wang(2), Jiawei Zhang(2)