In label-noise learning, the noise transition matrix, bridging the class posterior for noisy and
clean data, has been widely exploited to learn statistically consistent classifiers. The …

The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

Multi-label classification aims to learn classification models from instances associated with
multiple labels. It is pivotal to learn and utilize the label dependence among multiple labels …

Abstract Semi-Supervised Learning (SSL) has been an effective way to leverage abundant
unlabeled data with extremely scarce labeled data. However, most SSL methods are …

Aligning large language models (LLMs) with human preferences through reinforcement
learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward …

Label noise widely exists in large-scale image datasets. To mitigate the side effects of label
noise, state-of-the-art methods focus on selecting confident examples by leveraging semi …

In-context learning is a promising paradigm that utilizes in-context examples as prompts for
the predictions of large language models. These prompts are crucial for achieving strong …

In the presence of noisy labels, designing robust loss functions is critical for securing the
generalization performance of deep neural networks. Cross Entropy (CE) loss has been …

As one of the most fundamental techniques in multimodal learning, cross-modal matching
aims to project various sensory modalities into a shared feature space. To achieve this …

The success of deep learning is largely attributed to the training over clean data. However,
data is often coupled with noisy labels in practice. Learning with noisy labels is challenging …