Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 409 for “"Foundation Models"”.
-
Improving Foundation Models
Foundation models are the family of models (e.g. GPT-4, CLIP) that are trained on a massive dataset and perform various down-streaming tasks, usually with either zero- or few-shot learning, optionally after fine-tuning. This dissertation presents a wide range of important measures we have made to …
-
Scalable foundation models
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms
-
Towards Event Sequence Foundation Models
… in the power grid. This thesis proposes a foundation model approach to fault prediction, in which a transformer-based model is pretrained on large-scale event sequence datasets from diverse domains. We then fine-tune the model on downstream fault prediction tasks in a continual learning …
-
Mechanisms for generalization in foundation models
Modern machine learning models, and foundation models in particular—large-scale neural networks trained on large unstructured datasets—have demonstrated remarkable empirical success in generalizing to new data and adapting to downstream tasks with minimal additional training. Yet the mechanisms …
-
Toward Reliable Supervision for Foundation Models
Foundation models have made rapid progress in reasoning, alignment, and multimodal understanding, but their reliability critically depends on the quality of supervision used during learning. Such supervision may come from learned reward models, verifiable outcomes, expert models, the model itself, …
-
Adapting multimodal foundation models for recommendation
Multimodal foundation models (MFMs) now show strong representation and generation capabilities. Adapting them to recommender systems is a natural and increasingly central research direction, since items often contain rich multimodal signals such as text, images, videos, and audio. Yet MFMs are …
-
Holistic Diagnosis via Multimodal Foundation Models
… the recent success of small and large language models, it is natural to try and incorporate them with multimodal capabilities in the healtcare domain. This thesis seeks to investigate how well small language models can perform on predictive tasks in healthcare using multimodal data. To explore …
-
Taxonomic inference with DNA foundation models
… biology has catalyzed the development of foundation models pre-trained on genomic sequences, offering unprecedented capabilities in deciphering biological patterns. Concurrently, taxonomic identification through DNA fragment analysis remains a cornerstone of metagenomics, enabling the …
-
COMPOSITIONAL REASONING AND PLANNING WITH FOUNDATION MODELS
Foundation models are pre-trained by internet-scale data and possess vast knowledge. However, they struggle with compositional tasks in reasoning and planning. In those tasks, evidence is scattered across multiple sources and needs to be considered together simultaneously or connected in a …
-
DEEP REPRESENTATION LEARNING FOR VIDEO FOUNDATION MODELS
In this thesis, we focus on video foundation models. Specifically, we would like to investigate approaches for learning deep representations from videos, which is one of the most important topics with respect to the video foundation models. Three challenges are identified that potentially impede …
-
Scalable and Efficient Training of Foundation Models
… the growing size and complexity of modern foundation models introduce significant challenges in terms of training scalability, stability, and efficiency, imposing severe computational and memory bottlenecks on both pre-training and fine-tuning. The prohibitive resources demanded by …
-
ENHANCING TRUSTWORTHINESS AND SAFETY IN FOUNDATION MODELS
The rapid progress of foundation models has driven breakthroughs in computer vision, language, and speech generation. Yet, their widespread deployment also introduces critical challenges of trustworthiness, robustness, and safety. This dissertation advances theoretical foundations and practical …
-
Robot navigation and manipulation with foundation models
… cloud-sourced data have given rise to foundation models, powerful, reusable models excelling in vision and language tasks. Their generalizable perception and comprehension capabilities offer a promising path toward language-conditioned robotic navigation and manipulation.<br><br>This …
-
Towards Unified and Generalizable Multimodal Foundation Models
Recent advances in multimodal models have reshaped multimodal learning by leveraging large language models (LLMs) as backbones and integrating them with vision encoders or diffusion models. These approaches have achieved strong performance in either multimodal understanding or multimodal …
-
Accessible Foundation Models: Systems, Algorithms, and Science
The ever-increasing scale of foundation models, such as ChatGPT and AlphaFold, has revolutionized AI and science more generally. However, increasing scale also steadily raises computational barriers, blocking almost everyone from studying, adapting, or otherwise using these models for anything …
-
Language-Guided Video Understanding with Foundation Models
… and decisions must be made online. Recent foundation models provide a new opportunity to rethink video understanding as a language-guided inference problem. Leveraging this shift, this thesis investigates how Vision-Language Models (VLMs) and Large Language Models (LLMs) can be used to …
-
On the efficiency and privacy of foundation models
The task of generative modeling – building models which directly capture and represent distributions, has seen a surge of popularity in recent years. The massive-scale foundation models which underpin the advances in the field have incredible performance, but come at the cost of large computational …
-
Generative Models as Foundation Models for Computer Vision
… by the success of large language generative models as foundational models for Natural Language Processing tasks, and leveraging the fact that vision generative models can be trained on vast amounts of unlabeled or weakly labeled data, this dissertation explores the use of generative models …
-
Toward Robust, Responsible and Trustworthy Speech Foundation Models
L'abstract è presente nell'allegato / the abstract is in the attachment
Page 1 of 21