Single-cell ATAC-seq (scATAC-seq) enables high-resolution mapping of chromatin accessibility, yet privacy regulations and data size constraints hinder multi-institutional sharing. Federated learning (FL) offers a privacy-preserving alternative, but faces three fundamental barriers in scATAC-seq analysis: ultra-high dimensionality, extreme sparsity, and severe cross-institutional heterogeneity. We propose FL-Sailer, the first FL framework designed for scATAC-seq data. FL-Sailer integrates two key innovations: (i) adaptive leverage score sampling, which selects biologically interpretable features while reducing dimensionality by 80%, and (ii) an invariant VAE architecture, which disentangles biological signals from technical confounders via mutual information minimization. We provide a convergence guarantee, showing that FL-Sailer converges to an approximate solution of the original high-dimensional problem with bounded error. Extensive experiments on synthetic and real epigenomic datasets demonstrate that FL-Sailer not only enables previously infeasible multi-institutional collaborations but also surpasses centralized methods by leveraging adaptive sampling as an implicit regularizer to suppress technical noise. Our work establishes that federated learning, when tailored to domain-specific challenges, can become a superior paradigm for collaborative epigenomic research.

Estimating the 6D object pose is one of the core problems in computer vision and robotics. It predicts the full configurations of rotation, translation and size of a given object, which has wide applications including Virtual Reality (VR) [2], scene understanding [30], and [42, 57, 31, 49]. There are twodirections in 6D object pose estimation.

We address the fundamental problem of learning implicit surfaces for shape inference without the need of 3D supervision.

Experiments demonstrate that our editing scheme based on 3D-SDN is superior to its 2D counterpart.

We live in a three-dimensional world, and a proper understanding of its volumetric structure is crucial for acting and planning. However, we perceive the world mainly via its two-dimensional projections.

Research efforts on learning implicit 3D shapes without 3D supervision have primarily resorted to binary occupancy[26,34]asthe representation, aiming tomatch reprojected 3D occupancytothe given binary masks. Current worksadopting signed distance functions (SDF) either require apretrained deep shape prior [27] or are limited to discretized representations [14] that do not scale up with resolution.