{
  "id": 4169,
  "url": "https://arxiv.org/abs/2605.17671v1",
  "title": "PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment",
  "summary": "Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predic",
  "authors": "Michael Arbel, Basile Terver, Jean Ponce",
  "category": "research",
  "topics": "safety-alignment,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-17T22:04:01.000Z",
  "fetched_at": "2026-07-14T16:30:50.569Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4169",
  "original_url": "https://arxiv.org/abs/2605.17671v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}