Information retrieval
The science surrounding search engines is commonly referred to as information retrieval, in which algorithmic principles are developed to match user interests to the best information about those interests.
Google started as a result of our founders' attempt to find the best matching between the user queries and Web documents, and do it really fast. During the process, they uncovered a few basic principles: 1) best pages tend to be those linked to the most; 2) best description of a page is often derived from the anchor text associated with the links to a page. Theories were developed to exploit these principles to optimize the task of retrieving the best documents for a user query.
Search and Information Retrieval on the Web has advanced significantly from those early days: 1) the notion of ""information"" has greatly expanded from documents to much richer representations such as images, videos, etc., 2) users are increasingly searching on their Mobile devices with very different interaction characteristics from search on the Desktops; 3) users are increasingly looking for direct information, such as answers to a question, or seeking to complete tasks, such as appointment booking. Through our research, we are continuing to enhance and refine the world's foremost search engine by aiming to scientifically understand the implications of those changes and address new challenges that they bring.
Recent Publications
The Live Database: Firestore’s Scalable and Consistent Realtime Queries
David Gay
Ram Kesavan
Namita Lal
Per Jacobsson
Hui Wu
Matt Bell
Xijiao Li
2026
Preview abstract
Google’s Firestore is a NoSQL serverless database service that scales to millions of queries per second and petabytes of storage, serving over 8 million databases and 1.5 billion monthly active end users. A key reason for its popularity is its unique realtime query feature, which greatly simplifes web and mobile application development. Realtime queries allow an application to present an up-to-date and strongly-consistent view of the state of the database to the end-user, and to receive fast notifications of changes to the database state.
In this paper we present the architecture of the Firestore realtime stack, how it provides seamless scaling and high availability while supplying strongly-consistent responses to clients, including evaluations simulating workloads that represent large applications. We also explain how the Firestore SDK enables the application to deliver a smooth user experience through periods of network disconnection.
View details
Breaking the Loop: An Empirical Comparison of Strategies for Novelty and Freshness in YouTube Music
Robin Dumas
Gergo Varady
Murat Goksedef
Srivaths Ranganathan
Tracy Pesin
Zihuan Diao
Josh Moore
Yanwei Song
Mukai Lu
Bernardo Cunha
2026
Preview abstract
Continuously trained ranking models in music recommenders fall into feedback loops where previously consumed items dominate recommendations. This suppresses two distinct content classes: new releases (temporal freshness) and unlistened catalog items (novelty). Industry practitioners have a wide menu of interventions available, ranging from serving-time heuristics, training-data reweighting, architectural debiasing, to uncertainty-driven exploration, Each of which are well understood in academic settings. But live systems offer challenges with continuously ingested content, interconnected components, and practical limitations that counteract the findings from academic research.
We report online A/B results for six interventions and one combination experiment across four conceptual layers (serving, training, architecture, exploration) on the YouTube Music homepage. All interventions modify the ranking model or the serving layer that consumes it scores; candidate generation and other upstream components are held fixed. Architectural debiasing produced the largest reduction in popularity dominance but penalized new releases. Uncertainty-driven exploration with an SNGP head drove +7.7\% Day-1 new-release engagement at no measurable homepage cost, at the expense of artist diversity. Stacking the bias tower with uncertainty-weighted loss composed additively on popularity redistribution and artist diversity, but absorbed the singleton new-release lift. We close with practitioner-facing takeaways on which layer to intervene at, and the hidden costs of each choice.
View details
QBAT: Model-based Query Budget Autotuner for Clustering-based Approximate Nearest Neighbor Search
Jonghyun Bae
Tae Jun Ham
Alan Li
Yannis Papakonstantinou
Proceedings of the VLDB Endowment (2026), pp. 3091-3104
Preview abstract
Approximate nearest neighbor search (ANNS) is a critical component in modern data-intensive applications, but its performance is often hindered by the use of a static query budget parameter. This one-size-fits-all approach, even if well-tuned, fails to account for the varying difficulty of individual queries, inevitably leading to suboptimal latency on easy queries and poor accuracy on hard ones. This paper introduces QBAT, a query-aware budget autotuner designed to resolve this dilemma. By analyzing query-specific features offline, QBAT dynamically allocates an appropriate budget for each query. We explore two predictive models: a highly accurate gradient-boosted decision tree and a simple, interpretable heuristic formula derived using the AlphaEvolve framework. These models can optimize budget allocation for both system performance or recall consistency priorities. Evaluations on large-scale datasets demonstrate that QBAT reduces total searched budget by up to 68.8% in the consistency mode on ScaNN, the state-of-the-art clustering-based ANNS method, while simultaneously enforcing a strict per-query recall target, a scenario where static budgets are notoriously inefficient and wasteful.
View details
UniGeoCLIP: Unified Geospatial Contrastive Learning
Guillaume Astruc
Jan Hosang
Loic Landrieu
Paul-Edouard Sarlin
EarthVision Workshop at CVPR (2026)
Preview abstract
The growing availability of co-located geospatial data spanning aerial imagery, street-level views, elevation models, text, and geographic coordinates offers a unique opportunity for multimodal representation learning. We introduce UNIGEOCLIP, a massively multimodal contrastive framework to jointly align five complementary geospatial modalities in a single unified embedding space. Unlike prior approaches that fuse modalities or rely on a central pivot representation, our method performs all-to-all contrastive alignment, enabling seamless comparison, retrieval, and reasoning across arbitrary combinations of modalities. We further propose a scaled latitude-longitude encoder that improves spatial representation by capturing multi-scale geographic structure. Extensive experiments across downstream geospatial tasks demonstrate that UNIGEOCLIP consistently outperforms single-modality contrastive models and coordinate-only baselines, highlighting the benefits of holistic multimodal geospatial alignment. A reference implementation is available at https://gastruc.github.io/unigeoclip.
View details
GovSCH: An Open-Source Schema for Authoring Cybersecurity and AI Governance Documents
Ibrahim Waziri Jr.
New America, New America (2025)
Preview abstract
The increasing complexity of cybersecurity and artificial intelligence (AI) executive orders, frameworks, and policies has made translating high-level directives into actionable implementation a persistent challenge. Policymakers, framework authors, and engineering teams often lack a unified approach for interpreting and operationalizing these documents, resulting in inefficiencies, misalignment, and delayed compliance. While existing standards such as the Open Security Controls Assessment Language (OSCAL) address control-level specifications, no standardized, machine-readable format exists for authoring and structuring high-level governance documents. This gap hinders collaboration across disciplines and obscures critical directives’ underlying intent and rationale.
This report introduces Governance Schema (GovSCH), an open-source schema designed to standardize the authoring and translation of cybersecurity and AI governance documents into a consistent, machine-readable format. By analyzing prior executive orders, regulatory frameworks, and policies, GovSCH identifies common structures and authoring practices to create an interoperable model that bridges policymakers, regulatory framework authors, and engineering teams. This approach enables more precise articulation of policy intent, improves transparency, and accelerates the technical implementation of regulations. Ultimately, GovSCH aims to enhance collaboration, standardization, and efficiency in cybersecurity and AI governance.
View details
Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation
Zhen Qin
Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (2025)
Preview abstract
Large language models (LLMs) are increasingly integral to information retrieval (IR), powering ranking, evaluation, and AI-assisted content creation. This widespread adoption necessitates a critical examination of potential biases arising from the interplay between these LLM-based components. This paper synthesizes existing research and presents novel experiment designs that explore how LLM-based rankers and assistants influence LLM-based judges. We provide the first empirical evidence of LLM judges exhibiting significant bias towards LLM-based rankers. Furthermore, we observe limitations in LLM judges' ability to discern subtle system performance differences. Contrary to some previous findings, our preliminary study does not find evidence of bias against AI-generated content. These results highlight the need for a more holistic view of the LLM-driven information ecosystem. To this end, we offer initial guidelines and a research agenda to ensure the reliable use of LLMs in IR evaluation.
View details
Some of our teams
×
![]()