Related papers: One Stone, Four Birds: A Comprehensive Solution fo…

Pre-trained Language Models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding. Various Chinese PLMs have been successively proposed for learning better Chinese language…

Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate…

The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative,…

Contrastive learning has emerged as an essential approach for self-supervised learning in visual representation learning. The central objective of contrastive learning is to maximize the similarities between two augmented versions of an…

Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious features, such as background information to make decisions.…

Contrastive learning (CL) brought significant progress to various NLP tasks. Despite this progress, CL has not been applied to Arabic NLP to date. Nor is it clear how much benefits it could bring to particular classes of tasks such as those…

Robust control design for quantum unitary transformations has been recognized as a fundamental and challenging task in the development of quantum information processing due to unavoidable decoherence or operational errors in the…

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Last couple of years have witnessed a tremendous progress in self-supervised learning (SSL), the success of which can be attributed to the introduction of useful inductive biases in the learning process to learn meaningful visual…

Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visual environments. While existing enhancement approaches require additional training, rely on…

The question answering system can answer questions from various fields and forms with deep neural networks, but it still lacks effective ways when facing multiple evidences. We introduce a new model called SRQA, which means Synthetic Reader…

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative…

Click-through rate (CTR) prediction becomes indispensable in ubiquitous web recommendation applications. Nevertheless, the current methods are struggling under the cold-start scenarios where the user interactions are extremely sparse. We…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

In this paper, we propose a hierarchical contrastive learning framework, HiCL, which considers local segment-level and global sequence-level relationships to improve training efficiency and effectiveness. Traditional methods typically…

Extracting generalized and robust representations is a major challenge in emotion recognition in conversations (ERC). To address this, we propose a supervised adversarial contrastive learning (SACL) framework for learning class-spread…

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information…

In computational pathology, we often face a scarcity of annotations and a large amount of unlabeled data. One method for dealing with this is semi-supervised learning which is commonly split into a self-supervised pretext task and a…

Operational consistent query answering (CQA) is a recent framework for CQA based on revised definitions of repairs, which are built by applying a sequence of operations (e.g., fact deletions) starting from an inconsistent database until we…

Model quantization is critical for deploying large language models (LLMs) on resource-constrained hardware, yet recent work has revealed severe security risks that benign LLMs in full precision may exhibit malicious behaviors after…