weight initialization

A Theory of Initialisation's Impact on Specialisation ICLR 2025 ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints ICCV 2025 Fast Training of Sinusoidal Neural Fields via Scaling Initialization ICLR 2025 FedBaF: Federated Learning Aggregation Biased by a Foundation Model AISTATS 2025 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks ICLR 2025 NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance ICLR 2025 Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis ICLR 2025 Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement AAAI 2025 Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin JMLR 2025 WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models CVPR 2025 A2Q+: Improving Accumulator-Aware Weight Quantization ICML 2024 DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity NeurIPS 2024 Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models IJCAI 2024 How connectivity structure shapes rich and lazy learning in neural circuits ICLR 2024 If You Want to Be Robust, Be Wary of Initialization NeurIPS 2024 Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes EMNLP 2024 Initializing Models with Larger Ones ICLR 2024 Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation NeurIPS 2024 LEMON: Lossless model expansion ICLR 2024 MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters WACV 2024 Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields WACV 2024 SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher ECCV 2024 Unraveling the Gradient Descent Dynamics of Transformers NeurIPS 2024 AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks AAAI 2023 Can We Find Strong Lottery Tickets in Generative Models? AAAI 2023