Publications - Hanzhou Liu

Hanzhou Liu*, Jia Huang, Mi Lu, Srikanth Saripalli, Peng Jiang*. "Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting." International Conference on Learning Representations (ICLR), 2026. Scores 8-8-6-6 · Top 1.3% [Paper] [Project] [Code] [Demo]

Hanzhou Liu, Peng Jiang, Jia Huang, Mi Lu. "Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration." arXiv preprint, 2025. [Paper] [Code]

Hanzhou Liu, Binghan Liu, Chengkai Liu, Mi Lu. "DiNAT-IR: Exploring Dilated Neighborhood Attention for High-Quality Image Restoration." International Robotics & Automation Journal (IRAJ), 2025. [Paper] [Code]

Hanzhou Liu, Kai Yin, Zhitong Chen, Chenyue Liu, Ali Mostafavi. "FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL." Proceedings of the AAAI Symposium Series (AI-Driven Resilience), 2026. [Paper] [Code] [Dataset]

Hanzhou Liu, Chengkai Liu, Jiacong Xu, Peng Jiang, Mi Lu. "XYScanNet: A State Space Model for Single Image Deblurring." NTIRE Workshop, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [Paper] [Code] [Demo]

Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu. "DeblurDiNAT: A Lightweight and Effective Transformer for Image Deblurring." arXiv preprint, 2024. [Paper] [Code]

Chengkai Liu, Jianghao Lin, Jianling Wang, Hanzhou Liu, James Caverlee. "Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models." Resource-efficient Learning for Knowledge Discovery Workshop (RelKD), KDD 2024. 🏆 Best Paper Award [Paper]

Chengkai Liu, Jianghao Lin, Hanzhou Liu, Jianling Wang, James Caverlee. "Behavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation." The Conference on Information and Knowledge Management (CIKM), 2024. [Paper]

Hanzhou Liu, Binghan Li, Mi Lu, Yucheng Wu. "Real-world Image Deblurring via Unsupervised Domain Adaptation." International Symposium on Visual Computing (ISVC), 2023. [Paper]

Hanzhou Liu, Mi Lu. "A Crosswalk Stripe Detection Model Based on Gradient Similarity Tags." 7th International Conference on Image, Vision and Computing (ICIVC), 2022. [Paper]