Related papers: A Declarative System for Optimizing AI Workloads
Smart databases are adopting artificial intelligence (AI) technologies to achieve {\em instance optimality}, and in the future, databases will come with prepackaged AI models within their core components. The reason is that every database…
In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in…
Entity resolution, the task of identifying and merging records that refer to the same real-world entity, is crucial in sectors like e-commerce, healthcare, and law enforcement. Large Language Models (LLMs) introduce an innovative approach…
Over the past a few years, research and development has made significant progresses on big data analytics. A fundamental issue for big data analytics is the efficiency. If the optimal solution is unable to attain or not required or has a…
Although recent advancements in large language models (LLMs) have significantly improved their performance on various tasks, they still face challenges with complex and symbolic multi-step reasoning, particularly in mathematical reasoning.…
Designing agents that reason and act upon the world has always been one of the main objectives of the Artificial Intelligence community. While for planning in "simple" domains the agents can solely rely on facts about the world, in several…
Planning has been part of the core pursuit for artificial intelligence since its conception, but earlier AI agents mostly focused on constrained settings because many of the cognitive substrates necessary for human-level planning have been…
As declarative query processing techniques expand in scope --- to the Web, data streams, network routers, and cloud platforms --- there is an increasing need for adaptive query processing techniques that can re-plan in the presence of…
Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…
Machine learning models are being increasingly deployed to take, or assist in taking, complicated and high-impact decisions, from quasi-autonomous vehicles to clinical decision support systems. This poses challenges, particularly when…
Background: AI-powered code generation, fueled by Large Language Models (LLMs), is revolutionizing software development. Models like OpenAI's Codex and GPT-4, alongside DeepSeek, leverage vast code and natural language datasets. However,…
AI deployment increasingly resembles a pipeline of data transformation, fine-tuning, and agent interactions rather than a monolithic LLM job; recent examples include RLHF/RLAIF training and agentic workflows. To cope with this shift, we…
Database research and development often require a large number of SQL queries for benchmarking purposes. However, acquiring real-world SQL queries is challenging due to privacy concerns, and existing SQL generation methods are limited in…
Modern AI agents, driven by advances in large foundation models, promise to enhance our productivity and transform our lives by augmenting our knowledge and capabilities. To achieve this vision, AI agents must effectively plan, perform…
Large Language Models are increasingly deployed for decision-making, yet their adoption in high-stakes domains remains limited by miscalibrated probabilities, unfaithful explanations, and inability to incorporate expert knowledge precisely.…
Autonomous driving systems, critical for safety, require real-time guarantees and can be modeled as DAGs. Their acceleration features, such as caches and pipelining, often result in execution times below the worst-case. Thus, a…
Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data-driven framework to accelerate MPC by replacing online optimization with a nonparametric policy…
Training large foundation models costs hundreds of millions of dollars, making deployment optimization critical. Current approaches require machine learning engineers to manually craft training recipes through error-prone trial-and-error on…
Typical state of the art flow cytometry data samples consists of measures of more than 100.000 cells in 10 or more features. AI systems are able to diagnose such data with almost the same accuracy as human experts. However, there is one…
Synthesizing clinical evidence largely relies on systematic reviews of clinical trials and retrospective analyses from medical literature. However, the rapid expansion of publications presents challenges in efficiently identifying,…