{
  "id": 20845823,
  "title": "Raptor: Rejection-aware Adaptive Tree based on Speculative Decoding",
  "url": "https://urgent.news/2026/11/19/raptor-rejection-aware-adaptive-tree-based-on-speculative-decoding",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-19T03:17:52.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.25436v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Tree-structured speculative decoding accelerates vision-language models (VLMs) by verifying multiple candidate continuations in parallel. However, long visual contexts increase the cost of speculative computation, making candidate coverage and redundant expansion important considerations beyond tree topology adaptation. We propose Raptor, a training-free framework that uses rejection feedback to…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}