Related papers: Pre-training Language Model as a Multi-perspective…

In-context learning (ICL) with large language models (LLMs) delivers strong few-shot performance by choosing few-shot demonstrations from the entire training data. However, existing ICL methods, which rely on similarity or diversity scores…

In-Context Learning (ICL) enables large language models (LLMs) to achieve rapid task adaptation by learning from demonstrations. With the increase in available context length of LLMs, recent experiments have shown that the performance of…

Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine…

Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even after sophisticated data curation. A natural approach to better leverage high-quality data is…

Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream…

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power…

In the realm of recommendation systems, users exhibit a diverse array of behaviors when interacting with items. This phenomenon has spurred research into learning the implicit semantic relationships between these behaviors to enhance…

Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag…

The remarkable ability of Large Language Models (LLMs) to understand and follow instructions has sometimes been limited by their in-context learning (ICL) performance in low-resource languages. To address this, we introduce a novel approach…

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

Recent approaches have utilized self-supervised auxiliary tasks as representation learning to improve the performance and sample efficiency of vision-based reinforcement learning algorithms in single-agent settings. However, in multi-agent…

Speech Emotion Recognition (SER) in real-world scenarios remains challenging due to severe class imbalance and the prevalence of spontaneous, natural speech. While recent approaches leverage self-supervised learning (SSL) representations…

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable…

Existing work on continual learning (CL) is primarily devoted to developing algorithms for models trained from scratch. Despite their encouraging performance on contrived benchmarks, these algorithms show dramatic performance drops in…

Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multimodal data enhances…

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving…

Neural models have achieved great success on machine reading comprehension (MRC), many of which typically consist of two components: an evidence extractor and an answer predictor. The former seeks the most relevant information from a…

Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations.…

Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task…

The complexity of learning problems, such as Generative Adversarial Network (GAN) and its variants, multi-task and meta-learning, hyper-parameter learning, and a variety of real-world vision applications, demands a deeper understanding of…