Lngram: N-gram Conditional Memory in Latent Space 事件

Lngram: N-gram Conditional Memory in Latent Space arXiv:2605.24869v1 Announce Type: new Abstract: Sequence modeling requires both compositional reasoning and local static knowledge retrieval, yet standard Transformers handle both through dense computation. Engram partially decouples retrieval from the backbone, but its token-based keys remain tied to text tokenization and hash compression. We propose Lngram, a latent-space conditional memory module that learns discrete symbols directly from hid