相关论文: Improving Demonstration Diversity by Human-Free Fu…

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation…

We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to leverage their complementary strengths. One of the challenges of model fusion is high computational load, specifically in fine-tuning or aligning…

Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentation to help avoid overfitting. Previous Mixup-based methods…

Recent advancements in Text-to-SQL (Text2SQL) emphasize stimulating the large language models (LLM) on in-context learning, achieving significant results. Nevertheless, they face challenges when dealing with verbose database information and…

This work addresses the problem of optimizing communications between server and clients in federated learning (FL). Current sampling approaches in FL are either biased, or non optimal in terms of server-clients communications and training…

Dialogue generation models face the challenge of producing generic and repetitive responses. Unlike previous augmentation methods that mostly focus on token manipulation and ignore the essential variety within a single sample using hard…

There is often a mixture of very frequent labels and very infrequent labels in multi-label datatsets. This variation in label frequency, a type class imbalance, creates a significant challenge for building efficient multi-label…

Multi-label text classification (MLTC) is the task of assigning multiple labels to a given text, and has a wide range of application domains. Most existing approaches require an enormous amount of annotated data to learn a classifier and/or…

Text-to-SQL aims to convert natural language questions into executable SQL queries. While previous approaches, such as skeleton-masked selection, have demonstrated strong performance by retrieving similar training examples to guide large…

Large-scale cross-lingual language models (LM), such as mBERT, Unicoder and XLM, have achieved great success in cross-lingual representation learning. However, when applied to zero-shot cross-lingual transfer tasks, most existing methods…

Available works addressing multi-label classification in a data stream environment focus on proposing accurate models; however, these models often exhibit inefficiency and cannot balance effectiveness and efficiency. In this work, we…

Traditional dataset distillation primarily focuses on image representation while often overlooking the important role of labels. In this study, we introduce Label-Augmented Dataset Distillation (LADD), a new dataset distillation framework…

The performance of In-Context Learning (ICL) is highly sensitive to the selected demonstrations. Existing approaches to demonstration selection optimize different objectives, yielding inconsistent results. To address this, we propose a…

Large-scale dataset distillation requires storing auxiliary soft labels that can be 30-40x larger on ImageNet-1K and 200x larger on ImageNet-21K than the condensed images, undermining the goal of dataset compression. We identify two…

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can…

Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel…

While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior work has mostly been…

A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures. To comprehensively evaluate text-to-SQL systems, we introduce a UNIfied…

Clustering analysis of functional data, which comprises observations that evolve continuously over time or space, has gained increasing attention across various scientific disciplines. Practical applications often involve functional data…

Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique…