Biography
Runpei Dong is currently an M.S. student in Computer Science at Xi’an Jiaotong University. He collaborates closely with Prof. Kaisheng Ma, and he is also working with Prof. Li Yi. Before that, he received his bachelor’s degree in Computer Science from Xidian University in 2021. His current research interests include self-supervised 2D, 3D, and multimodal representation learning.
Interests
- Representation Learning
- Self-supervised Learning
- Efficient Machine Learning
- 3D Computer Vision
Education
Master Candidate in Computer Science, Now
Xi'an Jiaotong University
Bachelor in Computer Science, 2017 - 2021
Xidian University
Recent News
- [2023/01] One paper accepted at ICLR 2023.
- [2022/09] I join Megvii (Foundation Model Group) as a research intern.
- [2022/06] One paper accepted at ECCV 2022 (Oral).
- [2021/12] One paper accepted at ICML 2022.
- [2021/10] One paper accepted at BMVC 2021.
- [2021/06] One paper accepted at ISCA 2021.
Publications
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?.
In The 11th International Conference on Learning Representations (ICLR), 2023.
Contrastive Deep Supervision.
In The 17th European Conference on Computer Vision (ECCV), 2022. (Oral 2.7%)
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation.
Tech Report, May. 2022.
PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection.
Tech Report, May. 2022.
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks.
In The 39th International Conference on Machine Learning (ICML), 2022.
Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention.
In The 32nd British Machine Vision Conference (BMVC), 2021.
NN-Baton: DNN Workload Orchestration and Chiplet Granularity Exploration for Multichip Accelerators.
In ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), 2021.