Related papers: TADS: Task-Aware Data Selection for Multi-Task Mul…

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry. Their data curation poses the challenges of expensive human labeling, inadequate computing resources and larger experiment turn around…

The demand for machine learning (ML) model training on edge devices is escalating due to data privacy and personalized service needs. However, we observe that current on-device model training is hampered by the under-utilization of…

The search for suitable datasets is the critical "first step" in data-driven research, but it remains a great challenge. Researchers often need to search for datasets based on high-level task descriptions. However, existing search systems…

Task-oriented dialogues often require agents to enact complex, multi-step procedures in order to meet user requests. While large language models have found success automating these dialogues in constrained environments, their widespread…

We explore the potential of large-scale noisily labeled data to enhance feature learning by pretraining semantic segmentation models within a multi-modal framework for geospatial applications. We propose a novel Cross-modal Sample Selection…

The quality of datasets is one of the key factors that affect the accuracy of aerodynamic data models. For example, in the uniformly sampled Burgers' dataset, the insufficient high-speed data is overwhelmed by massive low-speed data.…

The limited scale of current 3D shape datasets hinders the advancements in 3D shape understanding, and motivates multi-modal learning approaches which transfer learned knowledge from data-abundant 2D image and language modalities to 3D…

Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in…

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this…

The deep learning-based analysis of medical images suffers from data scarcity because of high annotation costs and privacy concerns. Researchers in this domain have used transfer learning to avoid overfitting when using complex…

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality…

Multi-task learning (MTL) aims to improve the performance of a primary task by jointly learning with related auxiliary tasks. Traditional MTL methods select tasks randomly during training. However, both previous studies and our results…

Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance for modern industrial applications. However, building a system that is able to quickly and accurately pinpoint anomalous observations is a…

Metadata are general characteristics of the data in a well-curated and condensed format, and have been proven to be useful for decision making, knowledge discovery, and also heterogeneous data organization of biobank. Among all data types…

Deep neural networks have achieved impressive performance across a wide range of tasks, but this success often comes with substantial computational and storage costs due to large-scale training data. Dataset distillation addresses this…

Recently, the robotics community has amassed ever larger and more diverse datasets to train generalist robot policies. However, while these policies achieve strong mean performance across a variety of tasks, they often underperform on…

Fairness in machine learning seeks to mitigate model bias against individuals based on sensitive features such as sex or age, often caused by an uneven representation of the population in the training data due to selection bias. Notably,…

Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We…

Contrastive Language-Image Pretraining (CLIP) has shown impressive zero-shot performance on image classification. However, state-of-the-art methods often rely on fine-tuning techniques like prompt learning and adapter-based tuning to…

Large-scale general domain pretraining followed by downstream-specific finetuning has become a predominant paradigm in machine learning. However, discrepancies between the pretraining and target domains can still lead to performance…