Security-Enhanced Seed-Based Weight Quantization for Large Language Models

Excerpt

arXiv:2609.38477v1 Announce Type: cross 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 Feedb