{
  "id": 5770,
  "url": "https://arxiv.org/abs/2604.15121v1",
  "title": "SRMU: Relevance-Gated Updates for Streaming Hyperdimensional Memories",
  "summary": "Sequential associative memories (SAMs) are difficult to build and maintain in real-world streaming environments, where observations arrive incrementally over time, have imbalanced sampling, and non-stationary temporal dynamics. Vector Symbolic Architectures (VSAs) provide a biologically-inspired framework for building SAMs. Entities and attributes are encoded as quasi-orthogonal hyperdimensional vectors and processed with well defined algebraic operations. Despite this rich framework, most VSA s",
  "authors": "Shay Snyder, Andrew Capodieci, David Gorsich, Maryam Parsa",
  "category": "research",
  "topics": "environment,biotech",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-16T15:10:00.000Z",
  "fetched_at": "2026-07-14T16:32:02.057Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5770",
  "original_url": "https://arxiv.org/abs/2604.15121v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}