model sparsity

Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design ACL 2026 Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs EACL 2026 Improving Decision Sparsity NeurIPS 2024 Sparse maximal update parameterization: A holistic approach to sparse training dynamics NeurIPS 2024 Learning Adversarially Robust Sparse Networks via Weight Reparameterization AAAI 2023 Model Sparsity Can Simplify Machine Unlearning NeurIPS 2023 Rethinking Graph Lottery Tickets: Graph Sparsity Matters ICLR 2023 SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference ICML 2023 Compositional Generalization in Grounded Language Learning via Induced Model Sparsity NAACL 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 Sparse Double Descent: Where Network Pruning Aggravates Overfitting ICML 2022 SparTA: Deep-Learning Model Sparsity via Tensor-with-Sparsity-Attribute OSDI 2022 UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units NeurIPS 2022 ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity ICLR 2022 Channel Permutations for N:M Sparsity NeurIPS 2021 Minimally Invasive Surgery for Sparse Neural Networks in Contrastive Manner CVPR 2021 QUICKSAL: A small and sparse visual saliency model for efficient inference in resource constrained hardware WACV 2020 Sparse DNNs with Improved Adversarial Robustness NeurIPS 2018 Approximation Vector Machines for Large-scale Online Learning JMLR 2017