Brief Bio

I am a final-year Ph.D. Candidate at Huazhong University of Science and Technology, supervised by Prof. Xiang Bai. My research interests mainly lie in Embodied AI, 3D Object Analysis, World Model and Dense Object Analysis.

I was selected for the Youth Student Fundamental Research Project from NSFC (首批国家自然科学基金博士生项目入选者) and the Young Elite Scientists Sponsorship Program-Doctoral Student Special Plan from CAST (首批中国科协青年人才托举工程-博士生专项入选者), with a total funding of 340,000 RMB (~ 47,000 USD). Additionally, I have won multiple championships in top-tier computer vision competitions, which earned me a prize of 200,000 RMB (~ 28,000 USD).

I am open to research collaborations and internship opportunities. I have also mentored several undergraduate and graduate students who successfully published their work in top-tier conferences and journals. Please feel free to reach out to me via Email (dkliang@hust.edu.cn)🌟 or WeChat (liangdingkang)😄.
News


07 / 2025: One paper is accepted by ACM MM 2025
06 / 2025: Two papers are accepted by ICCV 2025
05 / 2025: Outstanding reviewer (6%) at CVPR 2025
04 / 2025: TransCrowd is selected as an Outstanding Paper (3.4%) in Science China Information Science (CCF A).
04 / 2025: We win 2nd place in SoccerNet Challenges on the Monocular Depth Estimation Track (CVPR 2025).
04 / 2025: I give a talk about VLM-based Driving Models in VOYAH company.
03 / 2025: I give a talk about 3D vision in CSIG Sharing Forum.
02 / 2025: Three papers are accepted by CVPR 2025
01 / 2025: One paper is accepted by ICLR 2025
01 / 2025: I was supported by the Young Elite Scientists Sponsorship Program-Doctoral Student Special Plan by CAST ( 首批中国科协青年人才托举工程-博士生专项), which is a grant of 40,000 RMB (~ 5,500 USD).
09 / 2024: I'm awarded National Scholarship
09 / 2024: I give a talk about dense object analysis in CSIG Student Member Sharing Forum.
09 / 2024: Three papers are accepted by NeurIPS 2024
09 / 2024: We win 1st place in the ECCV 2024 FishNet Classification Challenge.
08 / 2024: We win 2nd place in The First Dataset Distillation Challenge (ECCV 2024) on the Fixed IPC Track.
07 / 2024: One paper is accepted by ECCV 2024
04 / 2024: I was supported by the Youth Student Fundamental Research Project from NSFC ( 首批国家自然科学基金博士生项目), which is a grant of 300,000 RMB (~ 41,700 USD).
03 / 2024: FIDTM is selected as an ESI Highly Cited Paper (Top 1% of papers in the academic field)
02 / 2024: One paper is accepted by CVPR 2024
09 / 2023: Outstanding reviewer (1.5%) at ICCV 2023
09 / 2023: One paper is accepted by NeurIPS 2023
09 / 2023: TransCrowd is selected as an ESI Highly Cited Paper (Top 1% of papers in the academic field)
07 / 2023: One paper is accepted by ICCV 2023
03 / 2023: Two papers are accepted by CVPR 2023
01 / 2023: One paper is accepted by ICRA 2023
09 / 2022: Guided graduate students win 1st place in the VisDrone2022 (PRCV) challenge on the Crowd Counting Track.
08 / 2022: One paper is accepted by IEEE TMM
06 / 2022: Two papers are accepted by ECCV 2022
03 / 2022: We released the first comprehensive public African text dataset [project]
10 / 2021: I'm awarded National Scholarship
10 / 2021: One paper is accepted by IJCV
09 / 2021: We win 1st place in The VisDrone2021 (ICCV) Challenge on the Crowd Counting Track.
09 / 2020: We win 1st place in The VisDrone2020 (ECCV) Challenge on the Crowd Counting Track.
11 / 2019: We win 1st place in The CV101 (held by Extremevision and Intel), obtaining 180,000 RMB Bonus.
Wechat (welcome any discussion)


Selected publications (ALL )


(* Co-first author, # Corresponding author, + Project leader)

3D Understanding

Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
Dingkang Liang, Tianrui Feng, Xin Zhou, Yumeng Zhang, Zhikang Zou, Xiang Bai
IEEE TPAMI, 2025.
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
Xin Zhou*, Dingkang Liang*, Sifan Tu, Xiwu Chen, Yikang Ding, Dingyuan Zhang, Feiyang Tan, Hengshuang Zhao, Xiang Bai
ICCV, 2025. Paper. Code.
ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation
Haoyu Fu, Diankun Zhang, Zongchuang Zhao, Jianfeng Cui, Dingkang Liang+, Chong Zhang, Dingyuan Zhang, Hongwei Xie+, Bing Wang, Xiang Bai
ICCV, 2025. Paper. Code.
Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment
Xiaofan Li, Chenming Wu, Zhao Yang, Zhihao Xu, Dingkang Liang, Yumeng Zhang, Ji Wan, Jun Wang
ACM MM, 2025. Paper. Code.
Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception
Dingkang Liang, Dingyuan Zhang, Xin Zhou, Sifan Tu, Tianrui Feng, Xiaofan Li, Yumeng Zhang, Mingyang Du, Xiao Tan, Xiang Bai
Arxiv, 2025. Paper. Code.
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving
Zongchuang Zhao, Haoyu Fu, Dingkang Liang+, Xin Zhou, Dingyuan Zhang, Hongwei Xie, Bing Wang, Xiang Bai
Arxiv, 2025. Paper. Code.
The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey
Sifan Tu, Xin Zhou, Dingkang Liang, Xingyu Jiang, Yumeng Zhang, Xiaofan Li, Xiang Bai
Arxiv, 2025.
PointMamba: A Simple State Space Model for Point Cloud Analysis
Dingkang Liang, Xin Zhou, Wei Xu, Xingkui Zhu, Zhikang Zou, Xiaoqing Ye, Xiao Tan, Xiang Bai
NeurIPS, 2024.
DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection
Jingyu Li, Zhe Liu, Jinghua Hou, Dingkang Liang#
ICRA, 2023.
Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression
Dingyuan Zhang*, Dingkang Liang*, Zichang Tan, Xiaoqing Ye, Cheng Zhang, Jingdong Wang, Xiang Bai
ECCV, 2024.
A Unified Framework for 3D Scene Understanding
Wei Xu, Chunsheng Shi, Sifan Tu, Xin Zhou, Dingkang Liang+ , Xiang Bai
NeurIPS, 2024.
Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
Xin Zhou*, Dingkang Liang*, Wei Xu, Xingkui Zhu, Yihan Xu, Zhikang Zou, Xiang Bai
CVPR, 2024.
A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection
Dingyuan Zhang*, Dingkang Liang*, Zhikang Zou*, Jingyu Li, Xiaoqing Ye, Zhe Liu, Xiao Tan, Xiang Bai
ICCV, 2023.
LATFormer: Locality-Aware Point-View Fusion Transformer for 3D Shape Recognition
Xinwei He*, Silin Cheng*, Dingkang Liang*, Song Bai, Xi Wang, Yingying Zhu
Pattern Recognition, 2024.
Query-based Temporal Fusion with Explicit Motion for 3D Object Detection
Jinghua Hou, Zhe Liu, Dingkang Liang, Zhikang Zou, Xiaoqing Ye, Xiang Bai
NeurIPS, 2023.
SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model
DIngyuan Zhang, Dingkang Liang, Hongcheng Yang, Zhikang Zou, Xiaoqing Ye, Zhe Liu, Xiang Bai
SCIS, 2024.

Dense Object Analysis

MINIMA: Modality Invariant Image Matching
Xingyu Jiang, Jiangwei Ren, Zizhuo Li, Xin Zhou, Dingkang Liang, Xiang Bai
CVPR, 2025.
A Unified Image-Dense Annotation Generation Model for Underwater Scenes
Hongkai Lin, Dingkang Liang, Zhenghao Qi, Xiang Bai
CVPR, 2025.
SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection
Dingkang Liang, Wei Hua, Chunsheng Shi, Zhikang Zou, Xiaoqing Ye, Xiang Bai
Arxiv, 2024.
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
Dingkang Liang, Jiahao Xie, Zhikang Zou, Xiaoqing Ye, Wei Xu, Xiang Bai
CVPR, 2023.
An End-to-End Transformer Model for Crowd Localization
Dingkang Liang, Wei Xu, Xiang Bai
ECCV, 2022.
Focal inverse distance transform maps for crowd localization
Dingkang Liang, Wei Xu, Yingying Zhu, Yu Zhou
ESI Highly Cited Paper
IEEE TMM, 2022.
TransCrowd: weakly-supervised crowd counting with transformers
Dingkang Liang, Xiwu Chen, Wei Xu, Yu Zhou, Xiang Bai
ESI Highly Cited Paper
SCIS, 2022.
SOOD: Towards Semi-Supervised Oriented Object Detection
Wei Hua*, Dingkang Liang*, Jingyu Li, XiaoLong Liu, Zhikang Zou, Xiaoqing Ye, Xiang Bai
CVPR, 2023.
AutoScale: Learning to Scale for Crowd Counting
Chenfeng Xu*, Dingkang Liang*, Yongchao Xu, Song Bai, Wei Zhan, Xiang Bai, Massayoshi Tomizuka
IJCV, 2022.
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition
Bohan Li, Ye Yuan, Dingkang Liang, Xiao Liu, Zhilong Ji, Jinfeng Bai, Wenyu Liu, Xiang Bai
ECCV, 2022.

MLLM

Mini-Monkey: Multi-Scale Adaptive Cropping for Multimodal Large Language Models
Mingxin Huang, Yuliang Liu, Dingkang Liang, Lianwen Jin, Xiang Bai
ICLR, 2025.
From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
Xingkui Zhu, Yiran Guan, Dingkang Liang, Yuchao Chen, Yuliang Liu, Xiang Bai
NeurIPS, 2024.
Competition


  • The 1st place in the ECCV 2024 FishNet Classification Challenge
  • The 2nd place in The First Dataset Distillation Challenge (ECCV 2024) on the Fixed IPC Track
  • The 4th place of the 3D object detection track in CSIG-challenge 2022
  • Silver Award, China International College Students' "Internet+" Innovation and Entrepreneurship Competition (中国国际互联网+”大学生创新创业大赛全国总决赛), 2021.
  • The 1st place of the Crowd Counting track in Vision Meets Drone (VisDrone) challenge with ICCV 2021.
  • The 1st place of the Crowd Counting track in Vision Meets Drone (VisDrone) challenge with ECCV 2020.
  • The 1st place (100,000 RMB Bonus) of the Crowd Counting track in CV101 (held by Extremevision and Intel), Shenzhen, China, 2019.
  • The 1st place (80,000 RMB Bonus) of the OpenVino track in CV101 (held by Extremevision and Intel), Shenzhen, China, 2019.
  • Gold Award, China College Students' "Internet+" Innovation and Entrepreneurship Competition (中国互联网+”大学生创新创业大赛全国总决赛), 2019.
  • Grand Prize, "Challenge Cup" Competition, Provincial (挑战杯”江苏省大学生课外学术作品竞赛), 2019.
  • 全国大学生FPGA创新设计邀请赛国家级一等奖 (3,000 RMB Bonus), 2019.
  • 国家级大学生创新训练计划 (10,000 RMB Bonus),结题成绩优秀,入选第十一届全国大学生创新创业年会参展项目, 2018.
  • 全国大学生物联网设计竞赛华东赛区一等奖, 2018.
  • 江苏人工智能创新创业大赛优秀奖(10,000 RMB Bonus), 2018.
  • 全国大学生电子设计竞赛国家级二等奖, 2018.
  • 全国大学生FPGA创新设计邀请赛国家级二等奖, 2017.
  • “英飞凌”杯全国高校无人机创新设计应用大赛 Top 3.5% (14/400) (3,500 RMB Bonus), 2017.
  • Academic Services (Reviewer)


    Outstanding reviewer at ICCV 2023 and CVPR 2025
    • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • IEEE/CVF International Conference on Computer Vision (ICCV)
    • European Conference on Computer Vision (ECCV)
    • Neural Information Processing Systems (NeurIPS)
    • International Conference on Learning Representations (ICLR)
    • International Conference on Machine Learning (ICML)
    • AAAI Conference on Artificial Intelligence (AAAI)
    • ACM International Conference on Multimedia (ACM MM)
    • IEEE International Conference on Robotics and Automation (ICRA)
    • International Conference on 3D Vision (3DV)

    • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    • International Journal of Computer Vision (IJCV)
    • IEEE Transactions on Image Processing (TIP)
    • IEEE Transactions on Intelligent Transportation Systems (TITS)
    • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
    • Science China-Information Science (SCIS)
    Co-supervised Students


    As a passionate collaborator, I am always open to working with fellow researchers. I have had the privilege of co-supervising several talented students. If you are interested in collaborating, feel free to reach out to me.

    已毕业的研究生:
    • Dingyuan Zhang. Master degree, graduating in 2025. Now at Xiaomi. 一作ICCV 23, ECCV 24, RAL 24, SCIS 23.
    • Wei Hua. Master degree, graduating in 2024. Now at Jiangxi Electric Power Grid Corporation. 一作CVPR 23, ICDAR 23.
    • Jingyu Li. Master degree, graduating in 2024. Now Ph.D. at Fudan University. 一作ICRA 23.
    • Jianfeng Kuang. Master degree, graduating in 2023. Now at ByteDance. 一作ICDAR 23.

    Moments


    Last updated: 2025-07-26