24 citations · 83 across the 32 of their papers we have counts for
32 papers
"Skill Issues'': Data-Centric Optimization of Lakehouse Agents
Nicole Rose Schneider, Davide Ghilardi, Giacomo Piccinini +1
Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environment files that teach agents…
Not Your Usual Type(s): Data contracts as types across languages and engines
Aldrin Montana, Colin Marc, Luca Bigon +1
Composable data systems promise to let developers combine languages, engines, and catalogs without sacrificing a coherent user experience. In practice, however, pipeline-node bound…
GitLake: Git-for-data for the agentic lakehouse
Weiming Sheng, Jinlang Wang, Manuel Barros +3
We present GitLake, a Git-for-data design for an agent-first lakehouse. The system lifts single-table Iceberg snapshots into lakehouse-wide commits, branches, and merges, letting a…
Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents
Weiming Sheng, Jinlang Wang, Manuel Barros +3
Lakehouses are now the default substrate for analytics and AI, but they remain fragile under concurrent, untrusted change: schema mismatches often surface only at runtime, developm…
Querying Everything Everywhere All at Once: Supervaluationism for the Agentic Lakehouse
Jacopo Tagliabue
Agentic analytics is turning the lakehouse into a multi-version system: swarms of (human or AI) producers materialize competing pipelines in data branches, while (human or AI) cons…
Test-Time Optimization of Physical Query Plans with LLMs
Mehmet Hamza Erol, Xiangpeng Hao, Federico Bianchi +3
Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.g., runtime, memory, and I/O) using predefined heuristics and statistical models. Imp…
Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governance
Jacopo Tagliabue, Federico Bianchi, Ciro Greco
Even as AI capabilities improve, most enterprises do not consider agents trustworthy enough to work on production data. In this paper, we argue that the path to trustworthy agentic…
AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators
Jacopo Tagliabue
We explore AI-driven distributed-systems policy design by combining stochastic code generation from large language models (LLMs) with deterministic verification in a domain-specifi…
Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
Jacopo Tagliabue, Ciro Greco
Data lakehouses run sensitive workloads, where AI-driven automation raises concerns about trust, correctness, and governance. We argue that API-first, programmable lakehouses provi…
Eudoxia: a FaaS scheduling simulator for the composable lakehouse
Tapan Srivastava, Jacopo Tagliabue, Ciro Greco
Due to the variety of its target use cases and the large API surface area to cover, a data lakehouse (DLH) is a natural candidate for a composable data system. Bauplan is a composa…
Zerrow: True Zero-Copy Arrow Pipelines in Bauplan
Yifan Dai, Jacopo Tagliabue, Andrea Arpaci-Dusseau +2
Bauplan is a FaaS-based lakehouse specifically built for data pipelines: its execution engine uses Apache Arrow for data passing between the nodes in the DAG. While Arrow is known…
FaaS and Furious: abstractions and differential caching for efficient data pre-processing
Jacopo Tagliabue, Ryan Curtin, Ciro Greco
Data pre-processing pipelines are the bread and butter of any successful AI project. We introduce a novel programming model for pipelines in a data lakehouse, allowing users to int…
Bauplan: zero-copy, scale-up FaaS for data pipelines
Jacopo Tagliabue, Tyler Caraza-Harter, Ciro Greco
Chaining functions for longer workloads is a key use case for FaaS platforms in data applications. However, modern data pipelines differ significantly from typical serverless use c…
Reproducible data science over data lakes: replayable data pipelines with Bauplan and Nessie
Jacopo Tagliabue, Ciro Greco
As the Lakehouse architecture becomes more widespread, ensuring the reproducibility of data workloads over data lakes emerges as a crucial concern for data engineers. However, achi…
How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis
Federico Bianchi, Patrick John Chia, Mert Yuksekgonul +3
Negotiation is the basis of social interactions; humans negotiate everything from the price of cars to how to share common resources. With rapidly growing interest in using large l…
Building a serverless Data Lakehouse from spare parts
Jacopo Tagliabue, Ciro Greco, Luca Bigon
The recently proposed Data Lakehouse architecture is built on open file formats, performance, and first-class support for data transformation, BI and data science: while the vision…
E Pluribus Unum: Guidelines on Multi-Objective Evaluation of Recommender Systems
Patrick John Chia, Giuseppe Attanasio, Jacopo Tagliabue +5
Recommender Systems today are still mostly evaluated in terms of accuracy, with other aspects beyond the immediate relevance of recommendations, such as diversity, long-term user r…
(Vector) Space is Not the Final Frontier: Product Search as Program Synthesis
Jacopo Tagliabue, Ciro Greco
As ecommerce continues growing, huge investments in ML and NLP for Information Retrieval are following. While the vector space model dominated retrieval modelling in product search…
EvalRS 2023. Well-Rounded Recommender Systems For Real-World Deployments
Federico Bianchi, Patrick John Chia, Ciro Greco +5
EvalRS aims to bring together practitioners from industry and academia to foster a debate on rounded evaluation of recommender systems, with a focus on real-world impact across a m…
Reasonable Scale Machine Learning with Open-Source Metaflow
Jacopo Tagliabue, Hugo Bowne-Anderson, Ville Tuulos +3
As Machine Learning (ML) gains adoption across industries and new use cases, practitioners increasingly realize the challenges around effectively developing and iterating on ML sys…
EvalRS: a Rounded Evaluation of Recommender Systems
Jacopo Tagliabue, Federico Bianchi, Tobias Schnabel +4
Much of the complexity of Recommender Systems (RSs) comes from the fact that they are used as part of more complex applications and affect user experience through a varied range of…
"Does it come in black?" CLIP-like models are zero-shot recommenders
Patrick John Chia, Jacopo Tagliabue, Federico Bianchi +2
Product discovery is a crucial component for online shopping. However, item-to-item recommendations today do not allow users to explore changes along selected dimensions: given a q…
Contrastive language and vision learning of general fashion concepts
Patrick John Chia, Giuseppe Attanasio, Federico Bianchi +5
The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models. While most use cases are cast as specialized supervised learnin…
DAG Card is the new Model Card
Jacopo Tagliabue, Ville Tuulos, Ciro Greco +1
With the progressive commoditization of modeling capabilities, data-centric AI recognizes that what happens before and after training becomes crucial for real-world deployments. Fo…