parameter initialization

Unlocking Pre-trained Weights: Parameter Inheritance for Zero-Shot Initialization CVPR 2026 Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales ICML 2025 Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing NeurIPS 2024 Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes EMNLP 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers NeurIPS 2024 OneBit: Towards Extremely Low-bit Large Language Models NeurIPS 2024 XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage AISTATS 2024 Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation ICLR 2023 Expected Gradients of Maxout Networks and Consequences to Parameter Initialization ICML 2023 Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks NeurIPS 2023 Learning to Grow Pretrained Models for Efficient Transformer Training ICLR 2023 bert2BERT: Towards Reusable Pretrained Language Models ACL 2022 ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation EMNLP 2022 Few-shot initializing of Active Learner via Meta-Learning EMNLP 2022 Information Augmentation for Few-shot Node Classification IJCAI 2022 Why neural networks find simple solutions: The many regularizers of geometric complexity NeurIPS 2022 Meta Distant Transfer Learning for Pre-trained Language Models EMNLP 2021 Meta Learning and Its Applications to Natural Language Processing ACL 2021 On the Expected Complexity of Maxout Networks NeurIPS 2021 Pre-training Methods for Neural Machine Translation ACL 2021 Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract) AAAI 2021 Lipschitz Constrained Parameter Initialization for Deep Transformers ACL 2020 Transfer and Multi-Task Learning for Noun–Noun Compound Interpretation EMNLP 2018 Ensemble Learning for Multi-Source Neural Machine Translation COLING 2016 Improved Neural Network Initialization by Grouping Context-Dependent Targets for Acoustic Modeling Interspeech 2016