{
  "id": 17779,
  "url": "https://arxiv.org/abs/2608.02148",
  "title": "Douyin Multimodal Embedding Model Technical Report",
  "summary": "Multimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and targets into vectors, it powers industrial search and recommendation and underpins modern agents. Real-world platforms with complex modalities and massive-scale content, such as Douyin, Xiaohongshu, and YouTube, demand both efficiency under billion-scale indexing and fine-grained discrimination for hard matching. Existing MLLM embedding models rarely satisfy both. Contrastive models are efficient",
  "authors": "Haonan Chen, Chu Li, Zhicheng Wang, Yuanwei Liu, Yuanjiang Wang, Shaohua Jiang",
  "category": "research",
  "topics": "bias-fairness,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-02T20:00:00.000Z",
  "fetched_at": "2026-08-10T05:10:00.488Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/17779",
  "original_url": "https://arxiv.org/abs/2608.02148",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}