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.
Mnist handwritten digit database
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
NegBio-VAE introduces negative binomial latents with dispersion to handle overdispersion in discrete VAE models, yielding better reconstruction, generation, and downstream representations than Poisson VAE baselines.
Presents hue-, saturation-, luminance-equivariant GCNNs via a direct-image lifting layer that resolves invalid RGB issues in prior CEConv work and reports better OOD generalization plus sample efficiency.
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.
-
Towards Generalized Certified Robustness with Multi-Norm Training
CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.
-
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
-
Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
NegBio-VAE introduces negative binomial latents with dispersion to handle overdispersion in discrete VAE models, yielding better reconstruction, generation, and downstream representations than Poisson VAE baselines.
-
Learning Color Equivariant Representations
Presents hue-, saturation-, luminance-equivariant GCNNs via a direct-image lifting layer that resolves invalid RGB issues in prior CEConv work and reports better OOD generalization plus sample efficiency.