Related papers: Transferable Post-training via Inverse Value Learn…

Training deep networks requires various design decisions regarding for instance their architecture, data augmentation, or optimization. In this work, we find these training variations to result in networks learning unique feature sets from…

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large…

Deep learning models trained on large data sets have been widely successful in both vision and language domains. As state-of-the-art deep learning architectures have continued to grow in parameter count so have the compute budgets and times…

The growing popularity of transfer learning, due to the availability of models pre-trained on vast amounts of data, makes it imperative to understand when the knowledge of these pre-trained models can be transferred to obtain…

Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power…

Despite the continuous research and evolution of language models, they sometimes underperform previous versions. Existing approaches to overcome these challenges are resource-intensive, highlighting the need for alternatives that enable…

Purpose: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally network performance should be optimized by drawing the training and testing data from the same domain. In practice, however,…

Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating…

Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the knowledge learned in the…

In this report, we combine the idea of Wide ResNets and transfer learning to optimize the architecture of deep neural networks. The first improvement of the architecture is the use of all layers as information source for the last layer.…

Post-training of Large Language Models (LLMs) is crucial for unlocking their task generalization potential and domain-specific capabilities. However, the current LLM post-training paradigm faces significant data challenges, including the…

Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain. It is particularly important to neural networks, which are very likely to be overfitting. In some fields like…

Residual networks have shown great success and become indispensable in recent deep neural network models. In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of…

Multi-task post-training of large language models (LLMs) is typically performed by mixing datasets from different tasks and optimizing them jointly. This approach implicitly assumes that all tasks contribute gradients of similar magnitudes;…

The forward-forward algorithm presents a new method of training neural networks by updating weights during an inference, performing parameter updates for each layer individually. This immediately reduces memory requirements during training…

The post-training phase of large language models is essential for enhancing capabilities such as instruction-following, reasoning, and alignment with human preferences. However, it demands extensive high-quality data and poses risks like…

This paper addresses the problem of transferring useful knowledge from a source network to predict node labels in a newly formed target network. While existing transfer learning research has primarily focused on vector-based data, in which…

The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks without discriminating which part is necessary or unnecessary,…