SubLoRA projects the Hessian of the fine-tuning loss onto a submodular quadratic objective and uses greedy selection to automatically allocate LoRA ranks under a budget.
Foundation mod- els defining a new era in vision: a survey and outlook
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Automatic Rank Determination for Low-Rank Adaptation via Submodular Function Maximization
SubLoRA projects the Hessian of the fine-tuning loss onto a submodular quadratic objective and uses greedy selection to automatically allocate LoRA ranks under a budget.