Archives AI News

GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes

arXiv:2509.22953v1 Announce Type: new Abstract: Various deep generative models have been proposed to estimate potential outcomes distributions from observational data. However, none of them have the favorable theoretical property of general Neyman-orthogonality and, associated with it, quasi-oracle efficiency and double…

PLEIADES: Building Temporal Kernels with Orthogonal Polynomials

arXiv:2405.12179v5 Announce Type: replace Abstract: We introduce a class of neural networks named PLEIADES (PoLynomial Expansion In Adaptive Distributed Event-based Systems), which contains temporal convolution kernels generated from orthogonal polynomial basis functions. We focus on interfacing these networks with event-based…

LVT: Large-Scale Scene Reconstruction via Local View Transformers

arXiv:2509.25001v1 Announce Type: cross Abstract: Large transformer models are proving to be a powerful tool for 3D vision and novel view synthesis. However, the standard Transformer’s well-known quadratic complexity makes it difficult to scale these methods to large scenes. To…