Related papers: WAVE: Weight Templates for Adaptive Initialization…
The increasing scale and complexity of modern model parameters underscore the importance of pre-trained models. However, deployment often demands architectures of varying sizes, exposing limitations of conventional pre-training and…
The pre-training and fine-tuning paradigm has become the dominant approach for model adaptation. However, conventional pre-training typically yields models at a fixed scale, whereas practical deployment often requires models of varying…
In practice, we usually need to build variable-sized models adapting for diverse resource constraints in different application scenarios, where weight initialization is an important step prior to training. The Learngene framework,…
The training of diffusion models is computationally intensive, making effective pre-training essential. However, real-world deployments often demand models of variable sizes due to diverse memory and computational constraints, posing…
Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers…
Weight averaging is a widely used technique for accelerating training and improving the generalization of deep neural networks (DNNs). While existing approaches like stochastic weight averaging (SWA) rely on pre-set weighting schemes, they…
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 larger networks or was…
Large-scale general domain pretraining followed by downstream-specific finetuning has become a predominant paradigm in machine learning. However, discrepancies between the pretraining and target domains can still lead to performance…
Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization. Recent work shows that a specific initial parameter set can be learned from a population of supervised…
Neural network-based function approximation plays a pivotal role in the advancement of scientific computing and machine learning. Yet, training such models faces several challenges: (i) each target function often requires training a new…
Hybrid volumetric medical image segmentation models, combining the advantages of local convolution and global attention, have recently received considerable attention. While mainly focusing on architectural modifications, most existing…
While embeddings from multimodal large language models (LLMs) excel as general-purpose representations, their application to dynamic modalities like audio and video remains underexplored. We introduce WAVE (\textbf{u}nified \&…
Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent model merging methods, task vector has become a fundamental building block, as it can…
It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point. We explore the weights of such pre-trained Transformers (particularly for vision) to attempt to…
Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjusts the loss weight of each training sample based on its…
Here we propose the Reweighted Autoencoded Variational Bayes for Enhanced Sampling (RAVE) method, a new iterative scheme that uses the deep learning framework of variational autoencoders to enhance sampling in molecular simulations. RAVE…
Researches on deep neural networks with discrete parameters and their deployment in embedded systems have been active and promising topics. Although previous works have successfully reduced precision in inference, transferring both training…
Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming…
Pre-trained video large language models (Video LLMs) exhibit remarkable reasoning capabilities, yet adapting these models to new tasks involving additional modalities or data types (e.g., audio or 3D information) remains challenging. In…
We propose expanding the shared Transformer module to produce and initialize Transformers of varying depths, enabling adaptation to diverse resource constraints. Drawing an analogy to genetic expansibility, we term such module as learngene.…