{
  "id": 18416,
  "url": "https://arxiv.org/abs/2608.10720v1",
  "title": "Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence",
  "summary": "Omni-modal dialogue models can understand multimodal inputs and synthesize spoken replies, yet their responses remain visually disembodied. We introduce \\textbf{Ex-Omni-2D}, an omni-modal dialogue framework that generates a coordinated response comprising text, personalized speech, and reference-conditioned video. Given a multimodal query, reference image, and reference audio, the model predicts a structured \\textit{Visual Thought Plan} (VTP) describing scene, emotion, and motion, followed by re",
  "authors": "Haoyu Zhang, Zhipeng Li, Xiaoying Tang, Tianshu Yu, Yiwen Guo",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T09:37:11.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18416",
  "original_url": "https://arxiv.org/abs/2608.10720v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}