LATIDIA · Ciberseguridad

Cuantificación de peso basada en semillas de seguridad mejorada para modelos de lenguaje grandes

arXiv: 2609.38477v1Tipo de anuncio: nuevo Resumen: los modelos de lenguaje grandes (LLM) incurren en costos sustanciales de almacenamiento, ancho de banda de memoria y energía, lo que motiva representaciones de peso compactas. Método de compresión basado en semillas existente

La noticia

arXiv:2609.38477v1 Announce Type: new Abstract: Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-based compression methods reconstruct weights from compact pseudo-random representations but do not explicitly account for the non-uniform sensitivity of model weights. We introduce Seed-Q, a security-enhanced sensitivity-aware seed-based weight compression framework that uses lightweight Linear Feedback Shift Register (LFSR)-based weight generation with non-uniform bit allocation. Our approach assigns larger representation budgets to sensitive weights while aggressively compressing less sensitive regions. Importantly, this non-uniform allocation requires no side-information: the decoder deterministically reconstructs the bit-allocation schedule, with no rung depending on the decoded weights, eliminating the need to store per-block metadata