{
  "id": 25,
  "url": "https://arxiv.org/abs/2607.11008v1",
  "title": "SynCLIP: Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perception",
  "summary": "Open-vocabulary dense perception (OVDP) aims to localize objects unseen during training by leveraging textual knowledge. Despite the remarkable progress of recent CLIP-based approaches, we identify a critical limitation: synonym-induced grounding inconsistency, where semantically equivalent expressions yield disparate spatial attention patterns. This inconsistency undermines the robustness and performance of existing methods in real-world OVDP applications. To address this issue, we propose SynC",
  "authors": "Mingjie Xie, Guangjun He, Dongli Xu, Youtian Lin, Hongjue Li, Pengming Feng et al.",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-13T02:16:17.000Z",
  "fetched_at": "2026-07-14T14:14:15.664Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/25",
  "original_url": "https://arxiv.org/abs/2607.11008v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}