Tag
Proposes User as Engram, a method to store per-user memory as sparse local parametric edits in a hash-keyed memory table, inspired by hippocampal engrams, achieving better reasoning accuracy and memory efficiency compared to per-user LoRA.
Introduces a geometric framework to identify 'AI engrams' – memory traces in deep neural networks – formalizing neuroscientific criteria into a closed-form estimator, enabling surgical memory manipulation in models from MLPs to LLMs.
Weaviate launches Engram, a fully managed memory service for AI agents that actively maintains memory through reconciliation, deduplication, and scoped isolation, treating memory as infrastructure rather than data hoarding.