Dongfang Liu

Image Translation as Diffusion Visual Programmers

Qifan Wang, S. Dianat, James Liang, 2024, ArXiv.

Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?

Qifan Wang, Yiming Cui, Cheng Han, 2024, ICLR.

ProMotion: Prototypes As Motion Learners

Yingjie Chen, Zhiwen Cao, Yiming Cui, 2024, ArXiv.

SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving

Yiming Cui, Cheng Han, Dongfang Liu, 2024, ArXiv.

Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation

Yiming Cui, Cheng Han, Dongfang Liu, 2023, ACM Journal on Autonomous Transportation Systems.

AMD: Automatic Multi-step Distillation of Large-scale Vision Models

S. Dianat, Cheng Han, Qifan Wang, 2024, 2407.04208.