Papers Weight Space Learning
“Weight Space Learning” 태그가 달린 논문 6편 · 필터 해제
The Impact of Model Zoo Size and Composition on Weight Space Learning
Re-using trained neural network models is a common strategy to reduce training cost and transfer knowledge. Weight space learning - using the weights of trained models as data modality - is a promising new field to re-us…
DiversityTransfer LearningWeight Space LearningShape Generation via Weight Space Learning
Foundation models for 3D shape generation have recently shown a remarkable capacity to encode rich geometric priors across both global and local dimensions. However, leveraging these priors for downstream tasks can be ch…
3D Shape GenerationWeight Space LearningOn the Internal Representations of Graph Metanetworks
Weight space learning is an emerging paradigm in the deep learning community. The primary goal of weight space learning is to extract informative features from a set of parameters using specially designed neural networks…
Weight Space LearningDeep Linear Probe Generators for Weight Space Learning
Weight space learning aims to extract information about a neural network, such as its training dataset or generalization error. Recent approaches learn directly from model weights, but this presents many challenges as we…
Inductive BiasWeight Space LearningTowards Scalable and Versatile Weight Space Learning
Learning representations of well-trained neural network models holds the promise to provide an understanding of the inner workings of those models. However, previous work has either faced limitations when processing larg…
Representation LearningWeight Space LearningHyper-Representations for Pre-Training and Transfer Learning
Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Re…
Knowledge DistillationNeural Architecture SearchRepresentation LearningSelf-Supervised Learning+2