Wentong Li 李文通

College of Artificial Intelligence

Nanjing University of Aeronautics and Astronautics (NUAA)

Nanjing,China

     

About Me

I am an Associate Professor of the College of Artificial Intelligence at Nanjing University of Aeronautics and Astronautics. Previously, I completed my Ph.D at College of Computer Science and Technology, Zhejiang University, fortunately supervised by Prof. Jianke Zhu and Prof. Lei Zhang (PolyU, HK), in June 2024. My recent research interests are Visual/Scene Understanding, Embodied AI and Multimodal Large Language Models, particularly in:
1. Enabling MLLMs/VLMs with common visual tasks, including visual referring and grounding for image/video/3D scene.
2. Embodied scene understanding&reasoning, including ego-centric image/video analysis, reasoning and interaction, scene navigation.
3. Efficient and effective MLLMs, including token reduction, lightweight mllm, efficient high-resolution understanding.
Before, I mainly focus on the field of the techniques for object detection, image segmentaion and their weakly-supervised/label-efficient approaches. Besides, I am also interested in autonomous driving tasks (HD-Map, 3D-Occupancy, etc.) and 3D reconstruction tasks.

News

Preprints

photo
TokenPacker: Efficient Visual Projector for Multimodal LLM
Wentong Li*, Yuqian Yuan*, Jian Liu, Dongqi Tang, Song Wang, Jie Qin, Jianke Zhu, Lei Zhang
ArXiv:2407.02392, 2024
photo
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Yuqian Yuan, Hang Zhang, Wentong Li, Zesen Cheng, Boqiang Zhang, Long Li, Xin Li, Deli Zhao, Wenqiao Zhang, Yueting Zhuang, Jianke Zhu, Lidong Bing
ArXiv:2501.00599, 2025
photo
Scalable Autoregressive Monocular Depth Estimation
Jinhong Wang, Jian Liu, Dongqi Tang, Weiqiang Wang, Wentong Li, Danny Chen, Jian Wu
ArXiv:2411.11361, 2024
photo
ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning
Song Wang, Zhongdao Wang, Jiawei Yu, Wentong Li, Bailan Feng, Junbo Chen, Jianke Zhu
ArXiv:2409.18026, 2024

Selected Publications

photo
Osprey: Pixel Understanding with Visual Instruction Tuning
Yuqian Yuan*, Wentong Li*, Jian Liu, Dongqi Tang, Xinjie Luo, Chi Qin, Lei Zhang, Jianke Zhu
CVPR, 2024. (Project Leader)
photo
Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution
Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Risheng Yu, Xiansheng Hua, Lei Zhang
T-PAMI, 2024
photo
Label-efficient Segmentation via Affinity Propagation
Wentong Li*, Yuqian Yuan*, Song Wang, Wenyu Liu, Dongqi Tang, Jian Liu, Jianke Zhu, Lei Zhang
NeurIPS, 2023
photo
Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport
Wentong Li, Yuqian Yuan, Song Wang, Jianke Zhu, Jianshu Li, Jian Liu, Lei Zhang
ICCV, 2023
photo
Box-supervised Instance Segmentation with Level Set Evolution
Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Xiansheng Hua, Lei Zhang
ECCV, 2022
photo
Oriented RepPoints for Aerial Object Detection
Wentong Li, Yijie Chen, Kaixuan Hu, Jianke Zhu
CVPR, 2022
photo
Label-efficient Semantic Scene Completion with Scribble Annotations
Song Wang, Jiawei Yu, Wentong Li, Hao Shi, Kailun Yang, Junbo Chen, Jianke Zhu
IJCAI, 2024
photo
MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction
Xiaolu Liu, Song Wang, Wentong Li, Ruizi Yang, Junbo Chen, Jianke Zhu
CVPR, 2024
photo
Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation
Song Wang, Jiawei Yu, Wentong Li, Wenyu Liu, Junbo Chen, Jianke Zhu
CVPR, 2024

PaperCode

photo
Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering
Qiqun Gan, Wentong Li, Jinwei Ren, Jianke Zhu
AAAI, 2024

PaperCode

photo
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
Xue Yang, Gefan Zhang, Wentong Li, Xuehui Wang, Yue Zhou, Junchi Yan
ICLR, 2023
photo
LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation
Song Wang, Wentong Li, Wenyu Liu, Xiaolu Liu, Jianke Zhu
CVPR, 2023

PaperCode

Honors

Research Intern

Academic Services

Tech. Talks

Teaching Assistant

© Wentong Li | Last update: Jan. 2025