Skip to main content
Search

# Variational Autoencoder

16 related articles

Subscribe to updates
  1. bioRxiv

    A single-cell simulator with a dial for batch strength: scDeepSim varies batch effects and trajectory geometry on demand

    Benchmarking single-cell methods has been limited by costly annotation of real data and by datasets that capture only one observed condition. scDeepSim encodes expression into latent subvectors assigned to cell type, batch and residual variation, learns their distribution with latent diffusion, and at generation time modifies only the target subvector, imposing batch effects or constructing branching trajectories at user-set strengths. On scIB human pancreas data at intervention strength α=1, the structured model reached a mean cell-type silhouette width of 0.519 versus 0.432 for a plain variational autoencoder.

  2. A personal reference curve for brain wiring: BRIDGE cuts brain-age error by 3%–9% and ties deviation scores to ADOS in autistic boys

    Brain-connectivity differences in autism and other neurodevelopmental disorders have mostly been read from group-average case-control contrasts, which flatten individual variation. BRIDGE combines a graph variational autoencoder with normative modeling to learn an age-varying reference trajectory of structural connectomes from 1,164 neurotypical participants, then reports a global deviation score from brain-age difference and an individualized regional deviation map from regional embeddings. In 229 autistic children, the global score correlated with ADOS (Spearman R=−0.291) and IQ (Pearson R=0.195) in males, and brain-age prediction error was 3%–9% lower than comparable deep-learning models.

  3. arXiv

    No label required: six routine core-logging measurements already carry the geologist's lithology name, and a thousand-fold label weight only drops reconstruction from 0.999 to 0.836

    Marine drill cores no longer need a geologist's rock name as a training target. The usual practice treats shipboard lithology as the ground truth a model should reproduce, yet the six measurements logged on every core (bulk density, magnetic susceptibility, natural gamma radiation and three reflectance channels) are the properties geologists read when they assign that name. A masked variational autoencoder trained on 236,963 observations from 296 boreholes in the LILY database, without labels, separates lithologies as well as a semi-supervised variant (adjusted Rand index 0.237 against 0.247), and raising the label weight a thousand-fold only drops reconstruction from 0.999 to 0.836 while classification barely moves.

  4. medRxiv

    Compressing health records for causal analysis can drop a rare code, cutting mediation interval coverage to 2%

    Multimodal health records are often compressed into low-dimensional representations and used as adjustment sets, yet variational autoencoders are trained to reconstruct data rather than to preserve what causal identification needs. In simulations, a representation that discarded a rare code affecting both treatment and mediator gave 95% intervals for the interventional indirect effect with 2% coverage at n = 3,000 under moderate confounding, while reconstruction loss did not reveal the problem; a diagnostic comparing nuisance-function predictive loss flagged it in every replicate.

  5. arXiv

    Diffusion training drops the external vision encoder: reusing VAE features cuts SiT-XL/2 FID from 17.2 to 7.4

    CoVA recomposes the generative model's own VAE reconstruction features online into supervision with stronger semantics and spatial structure, cutting SiT-XL/2 FID on ImageNet 256x256 from 17.2 to 7.4 without an external vision encoder.

  6. arXiv

    Subsurface fracture networks skip fracture-by-fracture sampling: a latent diffusion model generates native 3D voxel fields and honors 84.2% of sparse well voxels

    Subsurface fracture networks were previously sampled fracture by fracture from prescribed statistics, which made sparse well observations hard to enforce. Here 2D and 3D networks are represented as binary occupancy fields, compressed by a variational autoencoder into a compact latent space, and learned by a diffusion model, with well observations injected through a learned conditioning encoder, classifier-free guidance, and diffusion posterior sampling. The 2D conditional model satisfies 99.6% of prescribed well observations, while the native 3D volumetric field satisfies 84.2% of observed well voxels while keeping fracture volume fraction close to the reference ensemble.

  7. arXiv

    A residual-spectrum instability theory explains cascading dimension-wise collapse in VAEs

    The work formulates dimension-wise posterior collapse in variational autoencoders as a fluctuation theory around partially collapsed states: treating the negative ELBO as an effective free energy, its quadratic expansion gives a Hessian acting as a mass matrix, collapsed directions form an invariant fluctuation sector whose exact mass spectrum follows from a conditional residual operator, and a local reactivation direction lowers the free energy once the decoder variance falls below the residual spectral upper edge, with equality marking marginality; numerical continuation shows latent dimensions lost near these spectral marginalities.

  8. arXiv

    MPAD synthesizes 3D multi-contrast MRI with 2D diffusion and multi-plane autoregression, cutting training FLOPs 7x and inference FLOPs 3x

    The authors propose MPAD: a 3D autoencoder compresses MRI volumes into an isotropic latent representation, a 2D diffusion model reconstructs masked target-contrast latent slices conditioned on source-contrast slices, unmasked target slices, and a text modality prompt, and inference generates slices autoregressively per plane while propagating completed volumes as priors to orthogonal planes, achieving full-volume 3D synthesis with 2D operations, reducing training and inference FLOPs by 7x and 3x versus 3D latent diffusion baselines, and improving PSNR, SSIM, and NMSE on ADNI and IXI.

  9. arXiv

    MeshCarve flow-matches in spatially compressed latents at 0.13 tokens per face, reaching the lowest Chamfer distance on Objaverse

    MeshCarve introduces a flow matching method that runs entirely in spatially compressed latents: a VAE generates coarse vertex occupancy in one forward pass as an anchor, then a vertex flow and an edge flow generate vertex positions and edge connections separately, with both latents learned by a VertexVAE and an EdgeVAE sharing a hierarchical sparse transformer backbone with spatial-aware compression and vertex-link encoding; its latent holds 0.13 tokens per face on average, achieving the lowest Chamfer distance and highest normal consistency on Objaverse and generalizing to Toys4K.

  10. arXiv

    Physics-guided variational autoencoder performs multi-modal surface wave inversion and is evaluated on an ultra-high-density dataset from the Devine test site in Texas

    The authors propose a physics-guided multi-modal variational autoencoder (PG-VAE) that uses a multi-stream fusion strategy to map independent latent features from raw shot gathers and spectral-dispersion images, a decoder with learned transposed convolutions and residual refinement to bias predictions toward layered earth models, and a differentiable surrogate network as a forward-consistency regularizer penalizing predictions that violate Rayleigh-wave dispersion physics; the network is trained on synthetic data from elastic modeling, validated on unseen synthetic data, and then evaluated on an ultra-high-density field dataset from the Devine test site in Texas, with Grad-CAM used to examine input features contributing to predictions.