DLR-Lock locks open-weight LLMs against unauthorized fine-tuning by swapping MLPs for deep low-rank residual networks that inflate backprop memory and complicate optimization, yet preserve original capabilities via module-wise distillation.
Convex optimization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
New MIP estimator for sparse PCA under spiked covariance model with statistical guarantees and custom solver scaling to 20,000 features.
QAOA ansatz with finite layers can capture any bitstring distribution and solves the Fair Cut Cover problem with provable and empirical advantages over classical approximations on certain graphs.
citing papers explorer
-
Locking Pretrained Weights via Deep Low-Rank Residual Distillation
DLR-Lock locks open-weight LLMs against unauthorized fine-tuning by swapping MLPs for deep low-rank residual networks that inflate backprop memory and complicate optimization, yet preserve original capabilities via module-wise distillation.
-
Sparse PCA: A New Scalable Estimator Based On Integer Programming
New MIP estimator for sparse PCA under spiked covariance model with statistical guarantees and custom solver scaling to 20,000 features.
-
Learning Cut Distributions with Quantum Optimization
QAOA ansatz with finite layers can capture any bitstring distribution and solves the Fair Cut Cover problem with provable and empirical advantages over classical approximations on certain graphs.