Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization
Jorge L. Ruiz Williams
KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted readout. We argue that pers…
cs.LG2026
Attention-Mass Condensation for Sparse Decoding
Jorge L. Ruiz Williams
Attention-mass concentration creates an opportunity for sparse decoding, but retained mass alone does not guarantee a stable greedy decision: retrieval error, omitted value directi…
cs.LG2026
Warp-Cortex: An Asynchronous, Memory-Efficient Architecture for Million-Agent Cognitive Scaling on Consumer Hardware
Jorge L. Ruiz Williams
Current multi-agent Large Language Model (LLM) frameworks suffer from linear memory scaling, rendering "System 2" parallel reasoning impractical on consumer hardware. We present Wa…