Related papers: MontePrep: Monte-Carlo-Driven Automatic Data Prepa…

Stream processing engines enable modern systems to conduct large-scale analytics over unbounded data streams in real time. They often view an application as a direct acyclic graph with streams flowing through pipelined instances of various…

Large language models (LLMs) are increasingly deployed in specialized production data processing pipelines across diverse domains -- such as finance, marketing, and e-commerce. However, when running them in production across many inputs,…

Modern recommendation models have increased to trillions of parameters. As cluster scales expand to O(1k), distributed training bottlenecks shift from computation and memory to data movement, especially lookup and communication latency…

Data preprocessing pipelines, which includes data decoding, cleaning, and transforming, are a crucial component of Machine Learning (ML) training. Thy are computationally intensive and often become a major bottleneck, due to the increasing…

We present AutoSiMP, an autonomous pipeline that transforms a natural-language structural problem description into a validated, binary topology without manual configuration. The pipeline comprises five modules: (1) an LLM-based configurator…

Recent multi-LLM agent systems have shown promising capabilities for automated problem-solving, yet they predominantly rely on frozen agents or static fine-tuning pipelines. To address this limitation, our primary contribution is ATLAS…

Current computer-aided synthesis planning (CASP) methods often treat retrosynthesis as solved once a single feasible route is identified, focusing primarily on convergence or shortest-path metrics. This view is misaligned with real-world…

Over the past decade, data science and machine learning has grown from a mysterious art form to a staple tool across a variety of fields in academia, business, and government. In this paper, we introduce the concept of tree-based pipeline…

Water scarcity and the low quality of wastewater produced in industrial applications present significant challenges, particularly in managing fresh water intake and reusing residual quantities. These issues affect various industries,…

Relational tables, where each row corresponds to an entity and each column corresponds to an attribute, have been the standard for tables in relational databases. However, such a standard cannot be taken for granted when dealing with tables…

Designing data integration pipelines typically requires substantial manual effort from data engineers to configure pipeline components and label training data. While LLMs have shown promise in handling individual steps of the integration…

Successful data-driven science requires complex data engineering pipelines to clean, transform, and alter data in preparation for machine learning, and robust results can only be achieved when each step in the pipeline can be justified, and…

In recent years, large language models (LLMs) have demonstrated significant potential in constructing passage retrieval datasets. However, existing methods still face limitations in expressing cross-doc query needs and controlling…

Standard Operating Procedures (SOPs) are critical for enterprise operations, yet existing language models struggle with SOP understanding and cross-domain generalization. Current methods fail because joint training cannot differentiate…

Machine-learning potentials (MLIPs) have been a breakthrough for computational physics in bringing the accuracy of quantum mechanics to atomistic modeling. To achieve near-quantum accuracy, it is necessary that neighborhoods contained in…

A desirable data selection algorithm can efficiently choose the most informative samples to maximize the utility of limited annotation budgets. However, current approaches, represented by active learning methods, typically follow a…

Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, current LLM agent tool planning methods typically rely on greedy,…

Dynamic programming (DP) is a fundamental method in operations research, but formulating DP models has traditionally required expert knowledge of both the problem context and DP techniques. Large Language Models (LLMs) offer the potential…

The analyst effort in data cleaning is gradually shifting away from the design of hand-written scripts to building and tuning complex pipelines of automated data cleaning libraries. Hyper-parameter tuning for data cleaning is very different…

Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted…