arXiv Machine Learning
Jun 8
Constructing VAE Latent Spaces with Prescribed Topology
arXiv:2606. 07058v1 Announce Type: new Abstract: Variational autoencoders (VAEs) learn low-dimensional latent representations of high-dimensional data.
Manifold-Matching Autoencoders: Embedding Data into Chosen Geometric Structures
Related stories
arXiv Machine Learning
Oct 15
Train to Stitch: Topology-Preserving Regularization for Interoperable Representations
arXiv:2610.19401v1 Announce Type: new Abstract: As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to be...
arXiv Machine Learning
Sep 1
Partially Linear Autoencoders for Manifold Learning and Dimensionality Reduction
arXiv:2608.29867v1 Announce Type: new Abstract: Autoencoders are widely used for nonlinear dimensionality reduction and manifold learning. While most common implementations rely on both nonlinear enc...
arXiv Machine Learning
Jun 17
Variational autoencoders with latent high-dimensional steady geometric flows for dynamics
arXiv:2410. 10137v5 Announce Type: replace Abstract: We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds.
arXiv AI
Oct 19
Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting
arXiv:2610.22439v1 Announce Type: cross Abstract: Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previo...
arXiv Machine Learning
Oct 21
LocaLeJEPA: Maximum Entropy Representations under Geometric Priors
LocaLeJEPA extends Joint-Embedding Predictive Architectures (JEPA) by introducing a manifold-theoretic reformulation that aligns representation learning with non‑Euclidean geometric priors. It incorporates a locally Euclidean distribution‑matching regularizer, LocaLeReg, to stabilize training and scale to large models. Experiments on ImageNet‑1K show that LocaLeJEPA outperforms the original LeJEPA across both hyperbolic and Euclidean backbones, improving linear and k‑NN classification as well as downstream tasks.
arXiv Machine Learning
Aug 27
Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-off
The paper investigates whether placing class prototypes on a hyperbolic manifold (Poincaré ball) rather than a Euclidean space improves the satisfaction of a tree‑structured regularizer in hierarchical classification. Experiments on WikiArt show that hyperbolic prototypes better preserve nearest‑neighbor topology (higher sibling and cousin recall) across multiple tree definitions, while Euclidean prototypes perform similarly to logistic regression on raw features and only hyperbolic models improve local retrieval. The study provides empirical evidence that the choice of latent geometry can affect the fidelity of tree‑structured regularization in real data.
arXiv Machine Learning
Aug 20
Enhancing Distance-Based Graph Autoencoders with Structural Penalties for Dynamic Graph Embedding
The paper introduces three distance‑based graph autoencoder variants that add structural penalties to the reconstruction loss. All models use a two‑layer Graph Convolutional Network encoder and a Euclidean‑distance decoder, with two node‑level regularizers: a hub penalty based on degree centrality and a penalty based on Natural Community Local Intrinsic Dimensionality (NC‑LID). Experiments on multiple dynamic graph datasets show that incorporating NC‑LID regularization consistently improves reconstruction performance compared to baselines without structural regularization and to the hub‑aware variant.
Hugging Face Trending Papers
Aug 25
Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-off
We study a tree-structured regularizer over class-prototype layouts in a hierarchical-classification model and ask whether the choice of latent manifold for the prototypes (Euclidean R^d vs. the Poinc...
arXiv Computer Vision
Oct 8
MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces
MeshCarve introduces a flow‑matching approach that generates artisan meshes entirely within compact latent spaces, separating vertex positions and edge connections to avoid joint encoding issues. It employs a hierarchical sparse transformer backbone with VertexVAE and EdgeVAE, which anchor on discrete vertices to drastically shorten token sequences and use spatial‑aware compression without sacrificing reconstruction quality. The method outperforms state‑of‑the‑art autoregressive and flow‑matching techniques on Objaverse and generalizes to Toys4K, representing one of the first fully compressed latent artisan mesh generators.
arXiv Machine Learning
Sep 1
Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching
arXiv:2608.28840v1 Announce Type: new Abstract: Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible,...
arXiv Machine Learning
Sep 7
Nested Inductive Bias Framework for SPD Manifold Learning
The paper introduces a Nested Inductive Bias framework that uses a two‑stage diffeomorphic composition to pull back non‑Euclidean target geometries onto symmetric positive definite (SPD) manifolds. This approach allows the construction of curvature‑aligned Riemannian classifiers that respect both matrix constraints and the intrinsic relational geometry of data. Empirical results on kinematic, signal processing, and synthetic benchmarks show that class separability degrades when metric curvature does not match the data distribution, and the authors also propose the Rational Conformal Metric (RCM) for robust vectorized architectures.