{
  "id": 14492,
  "url": "https://arxiv.org/abs/2607.23735v1",
  "title": "Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation",
  "summary": "In many real-world scenarios, encountering continual shifts in domain during inference is very common. Consequently, continual test-time adaptation (CTTA) techniques leveraging a teacher-student framework have gained prominence, allowing models to adapt continuously even after deployment. In such a framework, a weight-averaged mean teacher is used to produce pseudo-labels from test data for self-training. The mean teacher gets updated as an exponential moving average of the student parameters us",
  "authors": "Anurag Roy, Riddhiman Moulick, Vinay Kumar Verma, Saptarshi Ghosh, Abir Das",
  "category": "research",
  "topics": "children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-26T16:06:18.000Z",
  "fetched_at": "2026-07-29T05:10:12.205Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14492",
  "original_url": "https://arxiv.org/abs/2607.23735v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}