Haoyu He

8

Papers

12

Total Citations

Papers (8)

Efficient Stitchable Task Adaptation

Stitched ViTs are Flexible Vision Backbones

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility

Scalable Vision Transformers With Hierarchical Pooling

Dynamic Focus-Aware Positional Queries for Semantic Segmentation

Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning

EcoFormer: Energy-Saving Attention with Linear Complexity

Mask Propagation for Efficient Video Semantic Segmentation