Scholar
Yikang Ding
Google Scholar ID: gdP9StQAAAAJ
Tsinghua University
3D Vision
Generative Model
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
587
H-index
10
i10-index
10
Publications
20
Co-authors
22
list available
Contact
Email
dingyikang23@gmail.com
GitHub
Open ↗
Publications
11 items
Geometry-Instructed Video Editing
2026
Cited
0
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
2026
Cited
0
Kling-MotionControl Technical Report
2026
Cited
0
CLAIM: Camera-LiDAR Alignment with Intensity and Monodepth
2025
Cited
0
Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis
2025
Cited
0
Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
2025
Cited
0
ORV: 4D Occupancy-centric Robot Video Generation
2025
Cited
0
DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation
2025
Cited
0
Load more
Resume
Academic Achievements
- Publications: ICCV 2025 (DiST-4D, HERMES), BMVC 2025 (MuDG), CVPR 2025 (UniScene), ECCV 2024 (M2Depth), CVPR 2023 (Adaptive Assignment for Geometry Aware Local Feature Matching), CVPR 2022 (TransMVSNet), ECCV 2022 (KD-MVS), NeurIPS 2022 (WT-MVSNet)
- Awards: Innovation Award of 3D Occupancy Prediction Challenge in CVPR 2023
Research Experience
- Current Position: Researcher at KwaiVGI (Kling Team), working on generative models and AIGC
- Previous Position: Researcher at MEGVII (2023-2025), led a group on 3D reconstruction and generative models for autonomous driving
Education
- Master's Degree: Tsinghua University, 2020-2023
- Bachelor's Degree: Beihang University, 2016-2020
Background
- Research Interests: 3D Reconstruction, World Models, Generative Models, Computer Vision
- Work Experience: Currently a researcher at KwaiVGI (Kling Team), working on generative models and AIGC
- Education: M.S. from Tsinghua University (2020-2023), B.S. from Beihang University (2016-2020)
- Contact: dingyikang23@gmail.com, WeChat: yeecon_
Miscellany
- Other: Personal interests and hobbies not mentioned
Co-authors
15 total
Xiangyue Liu
Hong Kong University of Science and Technology (HKUST)
Qingtian Zhu
The University of Tokyo
Xiao Liu
Bytedance, Megvii, Tencent
Yingshuang Zou
Tsinghua University
Bohan Li
Shanghai Jiao Tong University
Pengzhi Li
Tsinghua University
Hao Zhao
Tsinghua University
Xiaojuan Qi
Assistant Professor, The University of Hong Kong