arXiv Machine Learning
Jun 4
Geometry-Preserving Encoder/Decoder in Latent Generative Models
arXiv:2501. 09876v3 Announce Type: replace-cross Abstract: Generative modeling aims to generate new data samples that resemble a given dataset.
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
arXiv:2602. 10099v2 Announce Type: replace Abstract: Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis.
Related stories
arXiv AI
Jun 8
STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
arXiv:2606. 07036v1 Announce Type: cross Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for large-scale training data for foundation models.
Hugging Face Trending Papers
Jul 27
RODR: Riemannian Orthogonally Decoupled Regularization for Disentangled Manifold Representation
Point cloud denoising is essentially a geometric recovery task that aims to reconstruct the intrinsic structure of a smooth 2D Riemannian manifold embedded in R^3 from noisy, discrete ambient-space samples. Despite the remarkable progress of modern manifold-aware encoders and generative transport models in geometric representation learning, a fundamental objective-geometry mismatch remains underexplored.
arXiv Machine Learning
Sep 24
On the Diffusibility of High-Dimensional Latents
The paper investigates how fine‑tuning pretrained visual encoders for faithful image reconstruction affects diffusion models that operate in the resulting latent space. It finds that such fine‑tuning reduces the effective dimensionality of the latent representation, causing standard velocity‑prediction flow‑matching to fit noise outside the low‑dimensional signal manifold and making optimization inefficient. Consequently, the authors propose using a clean‑data ($oldsymbol{x}_{0}$) parameterization, which focuses learning on the signal manifold and consistently improves text‑to‑image generation across multiple strong‑reconstruction encoders.
Hugging Face Trending Papers
Aug 5
Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds
We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds. While diffusion models (DMs) have achieved state-of-the-art results in high-dimensional data synthesis, they rely on large training datasets and ignore intrinsic geometric structure.
arXiv Machine Learning
Sep 23
When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds
arXiv:2609.25659v1 Announce Type: new Abstract: Many scientific datasets, such as molecular conformational ensembles or single-cell tissue measurements, are naturally modeled as meta-distributions: d...
arXiv Computer Vision
Sep 4
Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
The paper introduces a novel compression framework for image-to-shape Diffusion Transformers (DiTs) that significantly reduces model size while preserving geometric fidelity. By exploiting the non-uniform importance of 3D DiT layers, the authors combine structured pruning, adaptive quantization, and targeted fine‑tuning into a vitality‑guided approach. The method achieves up to a 66% reduction in model size across state‑of‑the‑art image‑to‑3D models without compromising synthesis quality, offering a plug‑and‑play solution for efficient 3D shape generation.
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 Machine Learning
Aug 6
Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds
arXiv:2608. 04827v1 Announce Type: cross Abstract: We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds.
arXiv Computer Vision
Aug 24
MeshFlow: Mesh Generation with Equivariant Flow Matching
arXiv:2606.23489v2 Announce Type: replace-cross Abstract: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains...
Hugging Face Trending Papers
Jul 21
Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-forward, deterministic regime, \ie~they cannot generate plausible geometry beyond what the input views directly support.
arXiv AI
Jun 2
Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
arXiv:2606. 00094v1 Announce Type: cross Abstract: Image generative models aim to sample data points from the underlying data manifold, a task that requires learning and decoding a dense, low-dimensional, and compact parameterization space.