I am currently a fourth-year Ph.D. student under the supervision of Prof. Yanwei Fu. My research interests focus on the perception and anticipation of motion, especially optical flow estimation and future prediction. Besides, I am also interested in image generation, e.g., image inpainting/editing. Currently, I am also working on multimodal large language models.
Education
Ph.D in Statistics (Machine Learning track) Fudan University
2022.9-2026.6 B.Sc. in Data Science Fudan University
2018.9-2022.6Services
• Reviewer of CVPR, ICCV, ECCV, AAAI, ACCV, IJCV, IEEE TPAMI, IEEE TCSVT, IEEE TIP, IEEE TMM
Publications
* indicates equal contributions.
Multimodal Large Lanuage Models:
Reinforcement Fine-Tuning Enables MLLMs Learning Novel Tasks Stably
Zhihao Zhang*, Qiaole Dong*, Qi Zhang, ..., Xuanjing Huang
Visual Perception:
Online Dense Point Tracking with Streaming Memory
Qiaole Dong, Yanwei Fu
MemFlow: Optical Flow Estimation and Prediction with Memory
Qiaole Dong, Yanwei Fu
Rethinking Optical Flow from Geometric Matching Consistent Perspective
Qiaole Dong*, Chenjie Cao*, Yanwei Fu
Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation
Qiaole Dong, Bo Zhao, Yanwei Fu
Visual Generation:
ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
Chenjie Cao*, Qiaole Dong*, Yanwei Fu
Learning Prior Feature and Attention Enhanced Image Inpainting
Chenjie Cao*, Qiaole Dong*, Yanwei Fu
Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding
Qiaole Dong*, Chenjie Cao*, Yanwei Fu
LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model
Chenjie Cao, Yunuo Cai, Qiaole Dong, Yikai Wang, Yanwei Fu
Repositioning the Subject within Image
Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, Yifan Li, Xiangyang Xue, Yanwei Fu
Others:
Causally-Aware Intraoperative Imputation for Overall Survival Time Prediction
Xiang Li*, Xuelin Qian*, Litian Liang*, Lingjie Kong, Qiaole Dong, ..., Yanwei Fu
