Related papers: A Flexible Selection Scheme for Minimum-Effort Tra…
Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…
Large language models may encounter factual knowledge during pre-training yet fail to reliably use that knowledge after fine-tuning. Despite growing empirical evidence that MLP layers store factual associations and fine-tuning affects…
Pre-trained language models can be fine-tuned to solve diverse NLP tasks, including in few-shot settings. Thus fine-tuning allows the model to quickly pick up task-specific ``skills,'' but there has been limited study of where these…
A pretrain-finetune strategy is widely used to reduce the overfitting that can occur when data is insufficient for CNN training. First few layers of a CNN pretrained on a large-scale RGB dataset are capable of acquiring general image…
Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and…
It is impossible today to pretend that the practice of machine learning is always compatible with the idea that training and testing data follow the same distribution. Several authors have recently used ensemble techniques to show how…
Convolutional Neural Networks (CNNs) are a standard approach for visual recognition due to their capacity to learn hierarchical representations from raw pixels. In practice, practitioners often choose among (i) training a compact custom CNN…
We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks. This problem has broad applications in NLP, such as targeted instruction tuning and data selection in…
Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities. In the zero-shot transfer setting, only English training data is used, and the…
Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity over fine-tuning due to its simplicity and improved…
The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs.…
Large pre-trained vision-language (VL) models have shown significant promise in adapting to various downstream tasks. However, fine-tuning the entire network is challenging due to the massive number of model parameters. To address this…
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…
Morphology-aware policy learning is a means of enhancing policy sample efficiency by aggregating data from multiple agents. These types of policies have previously been shown to help generalize over dynamic, kinematic, and limb…
As large-scale text-to-image generation models have made remarkable progress in the field of text-to-image generation, many fine-tuning methods have been proposed. However, these models often struggle with novel objects, especially with…
Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the…
Although massive pre-trained vision-language models like CLIP show impressive generalization capabilities for many tasks, still it often remains necessary to fine-tune them for improved performance on specific datasets. When doing so, it is…
Due to the computational complexity of evaluating interatomic forces from first principles, the creation of interatomic machine learning force fields has become a highly active field of research. However, the generation of training datasets…
In social media networks a small number of highly influential users can drive large scale changes in discourse across multiple communities. Small shifts in the behavior of these users are often sufficient to propagate widely throughout the…
State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not enable sharing…