Method Drift›Mixture-of-experts routing

Tracked

KBVQ-MoE

KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models

Mixture-of-experts routing · first seen Jan 30, 2026

current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.

BitsMoE BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
May 22, 2026
GEMQ GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
May 21, 2026
KBVQ-MoE KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
Jan 30, 2026
MC# (Mixture-Compressor-sharp)MC#: Mixture Compressor for Mixture-of-Experts Large Models
Oct 13, 2025