Related papers: A Billion-scale Foundation Model for Remote Sensin…
Artificial intelligence and machine learning have shown great promise in their ability to accelerate novel materials discovery. As researchers and domain scientists seek to unify and consolidate chemical knowledge, the case for models with…
Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintaining the general performance of the model while allowing it to gain new skills. A valuable goal…
Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly trained on. However, the architectures and pretraining objectives…
Scaling up model and data size have demonstrated impressive performance improvement over a wide range of tasks. Despite extensive studies on scaling behaviors for general-purpose tasks, medical images exhibit substantial differences from…
Automated behavior classification is essential for precision livestock farming but faces challenges of high computational costs and limited labeled data. This study systematically compared three approaches: training from scratch (ResNet-18,…
New geospatial foundation models introduce a new model architecture and pretraining dataset, often sampled using different notions of data diversity. Performance differences are largely attributed to the model architecture or input…
Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time series domains. Insofar as scaling has been a critical driver of performance of foundation models in…
Foundation models can be disruptive for future AI development by scaling up deep learning in terms of model size and training data's breadth and size. These models achieve state-of-the-art performance (often through further adaptation) on a…
Artificial Intelligence in medicine is traditionally limited by the lack of massive training datasets. Foundation models, pre-trained models that can be adapted to downstream tasks with small datasets, could alleviate this problem.…
Inspired by recent advances in large language models, foundation models have been developed for zero-shot time series forecasting, enabling prediction on datasets unseen during pretraining. These large-scale models, trained on vast…
As large-scale training regimes have gained popularity, the use of pretrained models for downstream tasks has become common practice in machine learning. While pretraining has been shown to enhance the performance of models in practice, the…
We investigate the impact of tokeniser pretraining on the accuracy and efficiency of physics emulation. Modern high-resolution simulations produce vast volumes of data spanning diverse physical regimes and scales. Training foundation models…
In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural…
Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different…
This thesis investigates how foundation models can be systematically leveraged to enhance robotic capabilities, enabling more effective localization, interaction, and manipulation in unstructured environments. The work is structured around…
Despite recent advancements in the field of medical image analysis with the use of pretrained foundation models, the issue of distribution shifts between cross-source images largely remains adamant. To circumvent that issue, investigators…
Despite the significant progress made by all-in-one models in universal image restoration, existing methods suffer from a generalization bottleneck in real-world scenarios, as they are mostly trained on small-scale synthetic datasets with…
While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size remain unclear, hindering effective model selection and…
Vision foundation models (VFMs) are pre-trained on extensive image datasets to learn general representations for diverse types of data. These models can subsequently be fine-tuned for specific downstream tasks, significantly boosting…
The increasing use of foundation models highlights the urgent need to address and eliminate implicit biases present in them that arise during pretraining. In this paper, we introduce PEFTDebias, a novel approach that employs…