3 papers
cs.CV2026
Hilbert-Guided Sparse Local Attention
Yunge Li, Lanyu Xu
The quadratic compute and memory costs of global self-attention severely limit its use in high-resolution images. Local attention reduces complexity by restricting attention to nei…
cs.CV2025
Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers
Yunge Li, Lanyu Xu
Vision Transformers (ViTs) have achieved remarkable success in visual recognition tasks, but redundant token representations limit their computational efficiency. Existing token me…
eess.IV2025
MTMed3D: A Multi-Task Transformer-Based Model for 3D Medical Imaging
Fan Li, Arun Iyengar, Lanyu Xu
In the field of medical imaging, AI-assisted techniques such as object detection, segmentation, and classification are widely employed to alleviate the workload of physicians and d…