M-DESIGN frames neural network refinement as retrieval over modification-gain graphs, with a Bayesian online update of task similarity and predictive planners for out-of-distribution cases, and reports reaching search-space optima in 26 of 33 graph task-data pairs within 100 evaluations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design
M-DESIGN frames neural network refinement as retrieval over modification-gain graphs, with a Bayesian online update of task similarity and predictive planners for out-of-distribution cases, and reports reaching search-space optima in 26 of 33 graph task-data pairs within 100 evaluations.