@inproceedings{eslami-etal-2026-diffusion,
    title = "Diffusion-Pretrained Dense and Contextual Embeddings",
    author = "Eslami, Sedigheh  and
      Gaiduk, Maksim  and
      Krimmel, Markus  and
      Milliken, Louis Mark  and
      Wang, Bo  and
      Bykov, Denis",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-form-platform/2026.acl-industry.69/",
    pages = "990--1004",
    ISBN = "979-8-89176-394-4",
    abstract = "We introduce pplx-embed, a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone for web-scale retrieval.By leveraging bidirectional attention through diffusion-based pretraining, our models capture comprehensive bidirectional context within passages, enabling the use of mean pooling to better preserve global context across long documents.We release pplx-embed-v1 for standard retrieval, and pplx-embed-context-v1 for contextualized embeddings that incorporate global document context into passage representations.pplx-embed-v1 achieves competitive performance on the MTEB(Multilingual, v2), MTEB(Code), BERGEN, and ToolRet retrieval benchmarks, while pplx-embed-context-v1 sets new records on the ConTEB benchmark."
}