Related papers: Wolf2Pack: The AutoFusion Framework for Dynamic Pa…

Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning (PEFT) methods have achieved strong task performance while…

Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different domains and datasets. This paper examines the approach of…

Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…

Discovering materials with desirable properties in an efficient way remains a significant problem in materials science. Many studies have tackled this problem by using different sets of information available about the materials. Among them,…

In this paper, we propose AutoCompete, a highly automated machine learning framework for tackling machine learning competitions. This framework has been learned by us, validated and improved over a period of more than two years by…

Model merging provides a cost-effective and data-efficient combination of specialized deep neural networks through parameter integration. This technique leverages expert models across downstream tasks without requiring retraining. Most…

In the health domain, decisions are often based on different data modalities. Thus, when creating prediction models, multimodal fusion approaches that can extract and combine relevant features from different data modalities, can be highly…

Selecting the best data mixture is critical for successful Supervised Fine-Tuning (SFT) of Multimodal Large Language Models. However, determining the optimal mixture weights across multiple domain-specific datasets remains a significant…

Multi-task visual perception has a wide range of applications in scene understanding such as autonomous driving. In this work, we devise an efficient unified framework to solve multiple common perception tasks, including instance…

Deep neural networks show great potential for automating various visual quality inspection tasks in manufacturing. However, their applicability is limited in more volatile scenarios, such as remanufacturing, where the inspected products and…

Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Recent progress has shown that merging can be highly effective…

Large diffusion-based Text-to-Image (T2I) models have shown impressive generative powers for text-to-image generation as well as spatially conditioned image generation. For most applications, we can train the model end-toend with paired…

The practical deployment of Federated Learning (FL) on resource-constrained devices is fundamentally limited by the high cost of training large models and the instability caused by heterogeneous (non-IID) client data. Conventional pruning…

While deep neural networks have demonstrated remarkable performance across various tasks, they typically require massive training data. Due to the presence of redundancies and biases in real-world datasets, not all data in the training…

Learning-based methods have been used to pro-gram robotic tasks in recent years. However, extensive training is usually required not only for the initial task learning but also for generalizing the learned model to the same task but in…

Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data…

Machine learning and deep learning methods have become essential for computer-assisted prediction in medicine, with a growing number of applications also in the field of mammography. Typically these algorithms are trained for a specific…

Personalized federated learning aims to address data heterogeneity across local clients in federated learning. However, current methods blindly incorporate either full model parameters or predefined partial parameters in personalized…

Recent advances in diffusion models have revolutionized text-guided image editing, yet existing editing methods face critical challenges in hyperparameter identification. To get the reasonable editing performance, these methods often…

Training AI models that generalize across tasks and domains has long been among the open problems driving AI research. The emergence of Foundation Models made it easier to obtain expert models for a given task, but the heterogeneity of data…