Xuening Zhu — accepted AI-conference papers

2025

Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction

Zhirui Gao, Renjiao Yi, Yaqiao Dai, Xuening Zhu, Wei Chen, Chenyang Zhu +1

ICCV 2025poster

This paper presents an end-to-end framework for reconstructing 3D parametric curves directly from multi-view edge maps. Contrasting with existing two-stage methods that follow a sequential "edge point cloud reconstruction and parametric curve fitting" pipeline, our one-stage approach optimizes 3D pa…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Sparse Autoencoders, Again?

Yin Lu, Xuening Zhu, Tong He, David Wipf

ICML 2025poster

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could reflect, among other things, correlation patterns in large lan…

Cited by 0 Source ↗PDF ↗Scholar ↗