Yifan Pu / 浦一凡

Ph.D. Student at Tsinghua University

My research focuses on computer vision and deep learning. I am currently interested in visual generation.

Selected Publications

* denotes equal contribution.

First Author

Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials

Y. Pu*, J. Ying*, T. Ye, et al.

NeurIPS 2025

ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

Y. Pu*, Y. Zhao*, Z. Tang, et al.

CVPR 2025

Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators

Y. Pu*, Z. Xia*, J. Guo*, et al.

ECCV 2024

Fine-grained Recognition with Learnable Semantic Data Augmentation

Y. Pu*, Y. Han*, Y. Wang, et al.

IEEE Transactions on Image Processing (TIP), 2024

Rank-DETR for High Quality Object Detection

Y. Pu*, W. Liang*, Y. Hao*, et al.

NeurIPS 2023

Adaptive Rotated Convolution for Rotated Object Detection

Y. Pu*, Y. Wang*, Z. Xia, et al.

ICCV 2023

Co-First Author

Bridging the Divide: Reconsidering Softmax and Linear Attention

D. Han*, Y. Pu*, Z. Xia, et al.

NeurIPS 2024

GRA: Detecting Oriented Objects through Group-wise Rotating and Attention

J. Wang*, Y. Pu*, Y. Han, et al.

ECCV 2024

Latency-aware Spatial-wise Dynamic Networks

Y. Han*, Z. Yuan*, Y. Pu*, et al.

NeurIPS 2022

Learning to Weight Samples for Dynamic Early-Exiting Networks

Y. Han*, Y. Pu*, Z. Lai, et al.

ECCV 2022