Zhiping Wu

LLMs can achieve superior KV cache compression by intelligently allocating quantization budgets between layer-wise and token-wise strategies, outperforming uniform or single-granularity approaches.

Riemannian Geometry-Sensitive Quantization (RGSQ), which formulates quantization as a reconstruction problem under a unified Fisher-Riemannian metric, enabling standard unimodal PTQ methods to evaluate multimodal quantization error under their original assumptions.

Autonomous racecars can now learn tire dynamics 71% faster and with 60% higher accuracy by "seeing" the road surface and remembering past driving behavior.