weight perturbation

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse ACL 2026 Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective ICCV 2025 STAR: Stability-Inducing Weight Perturbation for Continual Learning ICLR 2025 Improving robustness to corruptions with multiplicative weight perturbations NeurIPS 2024 PELA: Learning Parameter-Efficient Models with Low-Rank Approximation CVPR 2024 Training A Secure Model against Data-Free Model Extraction ECCV 2024 WeiPer: OOD Detection using Weight Perturbations of Class Projections NeurIPS 2024 Watermarking PLMs on Classification Tasks by Combining Contrastive Learning with Weight Perturbation EMNLP 2023 Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach NeurIPS 2022 NETWORK INSENSITIVITY TO PARAMETER NOISE VIA PARAMETER ATTACK DURING TRAINING ICLR 2022 NoiseGrad — Enhancing Explanations by Introducing Stochasticity to Model Weights AAAI 2022 Robust Weight Perturbation for Adversarial Training IJCAI 2022 Weight Perturbation as Defense against Adversarial Word Substitutions EMNLP 2022 Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations NeurIPS 2021 Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization AAAI 2021 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam ICML 2018 Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches ICLR 2018 Signal-to-Noise Ratio Analysis of Policy Gradient Algorithms NeurIPS 2008