{
  "annotation_id": "12feea47-3a02-44cf-bb3b-5862ee077757",
  "date_created": "2026-02-17T05:53:07.773000Z",
  "date_modified": "2026-02-17T05:53:07.773000Z",
  "file_hash": "0a6b2a91d8f3ed61da6d03908dea6ef51ee193e46fdcfd47e57898fa3c4494de",
  "private": false,
  "record": {
    "abstract": "Multimodal variational autoencoders (VAEs) are widely used for weakly supervised generative learning with multiple modalities. Predominant methods aggregate unimodal inference distributions using either a product of experts (PoE), a mixture of experts (MoE), or their combinations to approximate the joint posterior. In this work, we revisit multimodal inference through the lens of probabilistic opinion pooling, an optimization-based approach. We start from H\\\"older pooling with $\\alpha=0.5$, which corresponds to the unique symmetric member of the $\\alpha\\text{-divergence}$ family, and derive a moment-matching approximation, termed Hellinger. We then leverage such an approximation to propose HELVAE, a multimodal VAE that avoids sub-sampling, yielding an efficient yet effective model that: (i) learns more expressive latent representations as additional modalities are observed; and (ii) empirically achieves better trade-offs between generative coherence and quality, outperforming state-of-the-art multimodal VAE models.",
    "arxiv_id": "2601.06572",
    "authors": [
      "Huyen Khanh Vo",
      "Isabel Valera"
    ],
    "categories": [
      "cs.LG",
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Hellinger Multimodal Variational Autoencoders",
    "url": "https://arxiv.org/abs/2601.06572",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "70cead1e-1e18-46c3-805c-983b50df9ca4",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}