Xi Han (韩曦)

Xi Han (韩曦)

Ph.D. Student in Computer Science

Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

LBMamba: Locally Bi-directional Mamba

Published in arXiv preprint arXiv:2506.15976, 2025

We present LBVim, a scalable vision backbone that alternates scan directions every two layers to recover a global receptive field without extra backward sweeps. Jingwei Zhang and Xi Han contributed equally to this paper.

Recommended citation: Jingwei Zhang*, Xi Han*, Hong Qin, Mahdi S. Hosseini, and Dimitris Samaras, "LBMamba: Locally Bi-directional Mamba", arXiv preprint arXiv:2506.15976, 2025.
Download Paper

GeoMaNO: Geometric Mamba Neural Operator for Partial Differential Equations

Published in arXiv preprint arXiv:2505.12020, 2025

GeoMaNO is a geometry-aware Mamba neural operator for solving partial differential equations (PDEs). Xi Han and Jingwei Zhang contributed equally to this paper.

Recommended citation: Xi Han*, Jingwei Zhang*, Dimitris Samaras, Fei Hou, Hong Qin, "GeoMaNO: Geometric Mamba Neural Operator for Partial Differential Equations", arXiv preprint arXiv:2505.12020, 2025.
Download Paper

2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification

Published in Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

2DMamba is an efficient state space model for image representation, which extends 1D Mamba into 2D while maintaining its modeling capabilities, high parallelism, and memory access efficiency. Jingwei Zhang, Anh Tien Nguyen and Xi Han contributed equally to this paper.

Recommended citation: Jingwei Zhang*, Anh Tien Nguyen*, Xi Han*, Vincent Quoc-Huy Trinh, Hong Qin, Dimitris Samaras, and Mahdi S. Hosseini, "2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification", In Proceedings of the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
Download Paper

UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs

Published in Proceedings of the 41st International Conference on Machine Learning (ICML), 2024

UGrid is a fast-and-rirorous multigrid solver for linear Partial Differential Equations (PDEs).

Recommended citation: Xi Han, Fei Hou and Hong Qin, "UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs", In Proceedings of the 41st International Conference on Machine Learning (ICML), 2024.
Download Paper

Pose2Seg: Detection Free Human Instance Segmentation

Published in Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Detection Free Human Instance Segmentation.

Recommended citation: Song-Hai Zhang, Ruilong Li, Xin Dong, Paul Rosin, Zixi Cai, Xi Han, Dingcheng Yang, Haozhi Huang, and Shi-Min Hu, "Pose2seg: Detection free human instance segmentation", In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision And Pattern Recognition (CVPR), 2019.
Download Paper