{
  "id": 4127,
  "url": "https://arxiv.org/abs/2605.18257v1",
  "title": "CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook",
  "summary": "Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal information discrepancies and data scarcity, leading to suboptimal alignment spaces that overlook modality-unique features. We propose CodeBind, a framework that optimizes multimodal representation spaces through a modality-shared-specific codebook design. By incrementally aligning target and bridging modalities, CodeBind bypasses the need for fully paired ",
  "authors": "Zeyu Chen, Jie Li, Kai Han",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-18T11:56:19.000Z",
  "fetched_at": "2026-07-14T16:30:45.939Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4127",
  "original_url": "https://arxiv.org/abs/2605.18257v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}