Related papers: A CLIP-Powered Framework for Robust and Generaliza…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

The quality of pre-training data plays a critical role in the performance of foundation models. Popular foundation models often design their own recipe for data filtering, which makes it hard to analyze and compare different data filtering…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Recent advances in clinical AI have enabled remarkable progress across many clinical domains. However, existing benchmarks and models are primarily limited to a small set of modalities and tasks, which hinders the development of large-scale…

Implicit feedback, often used to build recommender systems, unavoidably confronts noise due to factors such as misclicks and position bias. Previous studies have attempted to alleviate this by identifying noisy samples based on their…

Helping end users comprehend the abstract distribution shifts can greatly facilitate AI deployment. Motivated by this, we propose a novel task, dataset explanation. Given two image data sets, dataset explanation aims to automatically point…

A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training. However, naively training a model on all available data may not be optimal (or feasible), as…

Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A…

Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of training on large amounts of noisy image-text data, without relying on expensive accurate labels used in standard vision unimodal supervised learning.…

Recent work shows that post-training datasets for LLMs can be substantially downsampled without noticeably deteriorating performance. However, data selection often incurs high computational costs or is limited to narrow domains. In this…

Large-scale Visual Instruction Tuning (VIT) has become a key paradigm for advancing the performance of vision-language models (VLMs) across various multimodal tasks. However, training on the large-scale datasets is computationally expensive…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Poor data quality limits the advantageous power of Machine Learning (ML) and weakens high-performing ML software systems. Nowadays, data are more prone to the risk of poor quality due to their increasing volume and complexity. Therefore,…

A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of the data points can be more representative or informative than others. This unequal importance…

Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Vulnerability detection is crucial for identifying security weaknesses in software systems. However, training effective machine learning models for this task is often constrained by the high cost and expertise required for data annotation.…

For classification tasks, deep neural networks are prone to overfitting in the presence of label noise. Although existing methods are able to alleviate this problem at low noise levels, they encounter significant performance reduction at…

Audio-visual zero-shot learning methods commonly build on features extracted from pre-trained models, e.g. video or audio classification models. However, existing benchmarks predate the popularization of large multi-modal models, such as…

We propose a novel, efficient, modular and scalable framework for content based visual media retrieval systems by leveraging the power of Deep Learning which is flexible to work both for images and videos conjointly and we also introduce an…

Training semantic segmenter with synthetic data has been attracting great attention due to its easy accessibility and huge quantities. Most previous methods focused on producing large-scale synthetic image-annotation samples and then…