3 papers
cs.LG2026
Proper Agnostic Learning of Affine Halfspaces under Log-Concave Marginals
Zhijie Zheng
We give a proper constant-factor agnostic learner for affine halfspaces under full-dimensional log-concave marginals. For arbitrary binary labels, the algorithm uses independent la…
cs.CV2026
RDGSplat: Render-Dedicated Geometry for Novel View Synthesis
Zhijie Zheng, Xinhao Xiang, Jiawei Zhang
Recent 3D foundation models extend to novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction. However, their rendering quality l…
cs.CV2026
PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling
Zhijie Zheng, Xinhao Xiang, Jiawei Zhang
Reconstructing 3D scenes from a single image is a fundamental challenge in computer vision, with broad applications in virtual reality, robotics, and content creation. Recent metho…