VSRAQ is a MoE-specific quantization objective that combines value and structure alignment to preserve expert-selection behavior and reduce quality loss without inference overhead.
Findings of the Association for Computational Linguistics: EMNLP 2024 , month = nov, year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models
VSRAQ is a MoE-specific quantization objective that combines value and structure alignment to preserve expert-selection behavior and reduce quality loss without inference overhead.