Related papers: Negative to Positive Co-learning with Aggressive M…

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

Traditional multimodal methods often assume static modality quality, which limits their adaptability in dynamic real-world scenarios. Thus, dynamical multimodal methods are proposed to assess modality quality and adjust their contribution…

The performance of Visio-Language Transformers drops sharply when an input modality (e.g., image) is missing, because the model is forced to make predictions using incomplete information. Existing missing-aware prompt methods help reduce…

Large language model unlearning aims to remove harmful information that LLMs have learnt to prevent their use for malicious purposes. LLMU and RMU have been proposed as two methods for LLM unlearning, achieving impressive results on…

Session-based recommendation aims to predict intents of anonymous users based on limited behaviors. With the ability in alleviating data sparsity, contrastive learning is prevailing in the task. However, we spot that existing contrastive…

Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep neural networks are prone to forgetting their previously…

Continual learning (CL) refers to the ability of an algorithm to continuously and incrementally acquire new knowledge from its environment while retaining previously learned information. A model trained on one data modality often fails when…

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than…

Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well…

While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit impressive representational capabilities for multimodal data, recent studies have revealed their vulnerability to backdoor attacks. To alleviate the threat, existing…

Improving artificial intelligence (AI) literacy has become an important consideration for academia and industry with the widespread adoption of AI technologies. Collaborative learning (CL) approaches have proven effective for information…

Multimodal learning often encounters the under-optimized problem and may have worse performance than unimodal learning. Existing methods attribute this problem to the imbalanced learning between modalities and rebalance them through…

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the…

We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…

Learning multi-lingual sentence embeddings is a fundamental task in natural language processing. Recent trends in learning both mono-lingual and multi-lingual sentence embeddings are mainly based on contrastive learning (CL) among an…

Continual learning aims to enable models to learn sequentially from continuously incoming data while retaining performance on previously learned tasks. With the Contrastive Language-Image Pre-trained model (CLIP) exhibiting strong…

We propose to improve transformers of a specific modality with irrelevant data from other modalities, e.g., improve an ImageNet model with audio or point cloud datasets. We would like to highlight that the data samples of the target…

Complementary-label learning (CLL) is widely used in weakly supervised classification, but it faces a significant challenge in real-world datasets when confronted with class-imbalanced training samples. In such scenarios, the number of…

Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called…

The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-based meta-learning attempts to address this challenging…