1 citations · 1 across the 5 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement
Akihiro Yoshida, Yuma Ichikawa
Mixed-precision weight quantization is commonly formulated as a Multiple-Choice Knapsack Problem (MCKP), yet existing solvers rely on scalar sensitivity proxies that collapse each…
cs.LG2026
OneComp: One-Line Revolution for Generative AI Model Compression
Yuma Ichikawa, Keiji Kimura, Akihiro Yoshida +11
Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the p…