Assigning 2, 3, or 4 bits to MoE experts by Hessian trace sensitivity keeps VLM accuracy close to uniform 4-bit while reducing model size.
Randomized algorithms for estimating the trace of an implicit symmetric positive semi- definite matrix
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
MoPEQ: Mixture of Mixed Precision Quantized Experts
Assigning 2, 3, or 4 bits to MoE experts by Hessian trace sensitivity keeps VLM accuracy close to uniform 4-bit while reducing model size.