相关论文: SemPipes -- Optimizable Semantic Data Operators fo…

Regulatory compliance reporting in the pharmaceutical industry relies on detailed tables, but these are often under-utilized beyond compliance due to their unstructured format and arbitrary content. Extracting and semantically representing…

As data science continues to grow in popularity, there will be an increasing need to make data science tools more scalable, flexible, and accessible. In particular, automated machine learning (AutoML) systems seek to automate the process of…

Monitoring unstructured streams increasingly requires persistent, semantics-aware computation, yet today's LLM frameworks remain stateless and one-shot, limiting their usefulness for long-running analytics. We introduce Continuous Prompts…

Automatic Speech Recognition has been a longstanding research area, with substantial efforts dedicated to integrating semi-supervised learning due to the scarcity of labeled datasets. However, most prior work has focused on improving…

AI-Integrated programming is emerging as a foundational paradigm for building intelligent systems with large language models (LLMs). Recent approaches such as Meaning Typed Programming (MTP) automate prompt generation by leveraging the…

Recent database systems have introduced semantic operators that leverage large language models (LLMs) to filter, join, and project over structured data using natural language predicates. In practice, these operators are combined with…

Exploratory analysis of high-dimensional data relies on embedding the data into a low-dimensional space (typically 2D or 3D), based on which visualization plot is produced to uncover meaningful structures and to communicate geometric and…

The deployment of Machine Learning (ML) models is a difficult and time-consuming job that comprises a series of sequential and correlated tasks that go from the data pre-processing, and the design and extraction of features, to the choice…

This paper proposes a semantic pilot design for data-aided channel estimation in text-inclusive data transmission, using a large language model (LLM). In this scenario, channel impairments often appear as typographical errors in the decoded…

Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text…

Pipeline parallelism is a crucial paradigm for large-scale model training. However, imbalances in memory footprint across stages can lead to significant GPU memory wastage, limiting the model sizes that pipeline parallelism can effectively…

Large language models (LLMs) are being increasingly deployed as part of pipelines that repeatedly process or generate data of some sort. However, a common barrier to deployment are the frequent and often unpredictable errors that plague…

Data preparation (DP) transforms raw data into a form suitable for downstream applications, typically by composing operations into executable pipelines. Building such pipelines is time-consuming and requires sophisticated programming…

Multi-product pipelines are a highly efficient means of transporting liquids. Traditionally used to transport petroleum, its products and derivatives, they are now being repurposed to transport liquified natural gas admixed with hydrogen of…

We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to…

Data cleaning is a long-standing challenge in data management. While powerful logic and statistical algorithms have been developed to detect and repair data errors in tables, existing algorithms predominantly rely on domain-experts to first…

Modern distributed data processing systems struggle to balance performance, maintainability, and developer productivity when integrating machine learning at scale. These challenges intensify in large collaborative environments due to high…

This paper presents a serverless MLOps framework orchestrating the complete ML lifecycle from data ingestion, training, deployment, monitoring, and retraining to using event-driven pipelines and managed services. The architecture is…

Tabular data analysis is crucial in many scenarios, yet efficiently identifying the most relevant data analysis queries and results for a new table remains a significant challenge. The complexity of tabular data, diverse analytical…

Pipelining is a well understood and often used implementation technique for increasing the performance of a hardware system. We develop several SystemC/C++ modeling techniques that allow us to quickly model, simulate, and evaluate…