{
  "id": 18656,
  "url": "https://arxiv.org/abs/2608.10989v1",
  "title": "Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers",
  "summary": "Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with different spatial demands. We ask which parts of a pruning policy transfer across image classification, semantic segmentation, and object detection. For each pipeline, controlled probes freeze the no-pruning checkpoint and apply a series of parameter-free reduction criteria at one eligible layer at a time without retraining. The probes reveal three differ",
  "authors": "Hongsen Cao, Mona Jaber, Shanxin Yuan, Ahmed Sayed",
  "category": "research",
  "topics": "regulation",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T14:43:52.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18656",
  "original_url": "https://arxiv.org/abs/2608.10989v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}