Pith. sign in

REVIEW 3 cited by

Generalized Multimodal ELBO

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2105.02470 v2 pith:Q7HSEGIS submitted 2021-05-06 cs.LG stat.ML

Thomas M. Sutter , Imant Daunhawer , Julia E. Vogt This is my paper · ORCID
classification cs.LGstat.ML
keywords dataelbolearningmodelsmultimodalgeneralizedgenerativeself-supervised
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multiple data types naturally co-occur when describing real-world phenomena and learning from them is a long-standing goal in machine learning research. However, existing self-supervised generative models approximating an ELBO are not able to fulfill all desired requirements of multimodal models: their posterior approximation functions lead to a trade-off between the semantic coherence and the ability to learn the joint data distribution. We propose a new, generalized ELBO formulation for multimodal data that overcomes these limitations. The new objective encompasses two previous methods as special cases and combines their benefits without compromises. In extensive experiments, we demonstrate the advantage of the proposed method compared to state-of-the-art models in self-supervised, generative learning tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Deep Generative Methods and Tire Architecture Design

    cs.LG 2025-07 conditional novelty 6.0 of 10

    On a proprietary tire-architecture dataset, diffusion models outperform VAEs and GANs overall; a masking-trained VAE beats MMVAE+ on component-conditioned generation, and MDM is best in-distribution while DDPM general...

  2. Differentiable neural network representation of multi-well, locally-convex potentials

    stat.ML 2025-06 conditional novelty 6.0 of 10

    A log-sum-exp mixture of input-convex neural networks fits multi-well potentials with learnable transition sharpness and sparse mode discovery.

  3. Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion

    cs.CV 2026-01 unverdicted novelty 5.0 of 10

    A regularization method enforces diverse intra-modal embeddings and bounded inter-modal drift to improve both multimodal fusion and unimodal robustness.

Pith tools