Related papers: EasyTUS: A Comprehensive Framework for Fast and Ac…

Extreme multi-label classification (XMC) is a popular framework for solving many real-world problems that require accurate prediction from a very large number of potential output choices. A popular approach for dealing with the large label…

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and…

Extracting structured information from text, such as key-value pairs that could augment tabular data, is quite useful in many enterprise use cases. Although large language models (LLMs) have enabled numerous automated pipelines for…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benchmark datasets have been proposed. However, existing…

Training deep learning models and performing hyperparameter tuning can be computationally demanding and time-consuming. Meanwhile, traditional machine learning methods like gradient-boosting algorithms remain the preferred choice for most…

Since 2020, automated testing for Database Management Systems (DBMSs) has flourished, uncovering hundreds of bugs in widely-used systems. A cornerstone of these techniques is test oracle, which typically implements a mechanism to generate…

Large Language Models (LLMs) have emerged as powerful tools for automating and executing complex data tasks. However, their integration into more complex data workflows introduces significant management challenges. In response, we present…

Fine-tuning pre-trained large language models (LLMs) has become a common practice for personalized natural language understanding (NLU) applications on downstream tasks and domain-specific datasets. However, there are two main challenges:…

Despite recent advances in large language models, open-source models often struggle to consistently perform well on complex reasoning tasks. Existing ensemble methods, whether applied at the token or output levels, fail to address these…

Data processing engines increasingly leverage distributed file systems for scalable, cost-effective storage. While the Apache Parquet columnar format has become a popular choice for data storage and retrieval, the immutability of Parquet…

Modern data science relies on data analytic pipelines to organize interdependent computational steps. Such analytic pipelines often involve different algorithms across multiple steps, each with its own hyperparameters. To achieve the best…

Retrieving mathematical knowledge is a central task in both human-driven research, such as determining whether a result already exists, finding related results, and identifying historical origins, and in emerging AI systems for mathematics,…

Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and efficient Test-Time Scaling (TTS) methods to unlock their full…

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access. To avoid code-intrusion…

In emerging scientific computing environments, matrix computations of increasing size and complexity are increasingly becoming prevalent. However, contemporary matrix language implementations are insufficient in their support for efficient…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Deep neural networks have emerged as a powerful technique for learning representations from user-item interaction data in collaborative filtering (CF) for recommender systems. However, many existing methods heavily rely on unique user and…

The rapid growth of publicly available textual resources, such as lexicons and domain-specific corpora, presents challenges in efficiently identifying relevant resources. While repositories are emerging, they often lack advanced search and…

Instruction Fine-Tuning (IFT) is crucial for aligning large language models (LLMs) with human preferences, and selecting a small yet representative subset from massive data significantly facilitates IFT in terms of both efficiency and…