model initialization

FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models CVPR 2026 Learngene: Inheritable ‘Genes’ in Intelligent Agents (Abstract Reprint) AAAI 2026 Differentially Private Learning Needs Better Model Initialization and Self-Distillation NAACL 2025 Optimizing Hidden Markov Language Models: An Empirical Study of Reparameterization and Initialization Techniques NAACL 2025 Slamming: Training a Speech Language Model on One GPU in a Day ACL 2025 WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models CVPR 2025 BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts NeurIPS 2024 Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers NeurIPS 2024 Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models IJCAI 2024 From Generalization Analysis to Optimization Designs for State Space Models ICML 2024 Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation NeurIPS 2024 Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors ICLR 2024 Transformer as Linear Expansion of Learngene AAAI 2024 XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage AISTATS 2024 A Bayesian Approach To Analysing Training Data Attribution In Deep Learning NeurIPS 2023 A Natural Bias for Language Generation Models ACL 2023 Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models? ICML 2023 GEMS: Generating Efficient Meta-Subnets WACV 2023 Magneto: A Foundation Transformer ICML 2023 Mimetic Initialization of Self-Attention Layers ICML 2023 Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning ICLR 2023 Learngene: From Open-World to Your Learning Task AAAI 2022 A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning ICML 2021 Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks NeurIPS 2021 Few-Round Learning for Federated Learning NeurIPS 2021