Dissecting Language Models: Machine Unlearning via Selective Pruningby Nicholas Pochinkov, Nandi SchootsFirst submitted to arxiv…
Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Spaceby Mahsa Mozafari-Nia, Salimeh Yasaei…
Verification of Neural Networks’ Global Robustnessby Anan Kabaha, Dana Drachsler-CohenFirst submitted to arxiv on: 29…
Masks, Signs, And Learning Rate Rewindingby Advait Gadhikar, Rebekka BurkholzFirst submitted to arxiv on: 29…
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimizationby Taisuke Yasuda, Kyriakos Axiotis, Gang Fu,…
Personalized Federated Instruction Tuning via Neural Architecture Searchby Pengyu Zhang, Yingbo Zhou, Ming Hu, Junxian…
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocationby Peng Xu, Wenqi Shao, Mengzhao…
Shaving Weights with Occam’s Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihoodby Rayen…
How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?by Hongkang Li, Meng Wang, Songtao…
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Modelsby…