arXiv subjects

Juan Lavista Ferres

Publications and source records attributed to Juan Lavista Ferres.

At least 19 recordsLinked to original sources

arXiv2026

Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute Backend

Applying deep learning models to satellite imagery from within geographic information systems (GIS) remains high-friction for remote sensing practitioners. Models arrive in incompatible formats and target different compute environments, from local workstations to serverless cloud services. As a result, every evaluation demands custom deployment, tiling, and georeferencing code before a single prediction reaches the analyst's map. This friction discourages systematic comparison in a domain where model choice directly affects operational outcomes such as field delineation, crop monitoring, and disaster response. We present Anaximander, an open-source system that unifies model source and compute location choice behind one interactive interface. The system's backend is an inference server that loads models from multiple commonly-used sources and serves them on any accessible compute backend. The server provides session management and model caching, and streams results back per tile. The backend is paired with a QGIS plugin that drives tiling, result reassembly, georeferencing, and real-time per-tile status visualization. An additional user-interface path injects layer legends as prompts into vision-language models. We demonstrate the system in a code-free side-by-side comparison of three heterogeneous models on an agricultural field delineation task: gpt-image-1 via a cloud API, Segment Anything Model 3 (SAM3) on a remote GPU, and DelineateAnything on a local CPU. The inference backend and protocol are open-source and available at https://github.com/microsoft/nxmndr.

cs.CV↗

arXiv2026

The Living Library: Transforming Archival Collections into Conversational Knowledge Systems -- Lessons from the Theodore Roosevelt Presidential Library

We present the Living Library, an end-to-end framework for transforming fragmented digital archives into governed, conversational, in-person exhibit experiences. Developed and deployed at the Theodore Roosevelt Presidential Library, the framework comprises four layers: digitization and corpus creation, AI-powered processing, retrieval and reasoning, and an optional embodied conversational interface. The first three layers aggregate a 300,000-record collection, apply OCR and structured metadata enrichment for expert curatorial review, and publish records to a hybrid dense/semantic index. Expert review is conducted through the Archivist App, a curator-facing interface that supports correction of AI-generated transcriptions and metadata. The governed corpus powers both a researcher-facing interface and Talk to TR, a continuously operating exhibit that embodies Theodore Roosevelt as a full-scale digital human within a museum environment. To support live, face-to-face interactions, Cross-Era Analogical Grounding reframes contemporary questions through documented historical parallels, allowing Roosevelt to address present-day topics without inventing facts. Dual-path retrieval and end-to-end streaming keep responses grounded and responsive. Layered watchdogs, visitor-session isolation, automated conversation management, and independently restartable services enable reliable unattended operation for hundreds of visitors. Avatar realism, spatial audio, lighting, staging, and conversational design are developed and evaluated as an integrated experience. Rather than report a controlled benchmark, we describe lessons from operating Talk to TR as a public exhibit and offer a transferable model for transforming archival collections into believable, in-person conversational experiences.

cs.CV↗

arXiv2026

WATCH: Wide-Area Archaeological Site Tracking for Change Detection

Monitoring archaeological sites at scale is vital for protecting cultural heritage, yet pinpointing when disturbances occur remains difficult because visual cues are subtle and ground-truth data are sparse. We introduce WATCH, a framework for month-level change-event localization over PlanetScope satellite mosaics (2017-2024, 4.7 m/px) that supports three complementary scoring approaches: (i) Temporal Embedding Distance (TED), a training-free method that scores month-to-month deviations from a local temporal reference; (ii) Self-Supervised Change Detection (SSCD), an ensemble of reconstruction, forecasting, and latent-novelty signals; and (iii) a Weakly Supervised (WS) temporal localization model trained with sparse event-month labels. We benchmark WATCH on 1,943 archaeological sites in Afghanistan using embeddings from six foundation models (CLIP, GeoRSCLIP, SatMAE, Prithvi-EO-2.0, DINOv3, and Satlas-Pretrain) alongside a handcrafted spectral and texture baseline, and assess cross-regional generalization on sites in Syria, Turkey, Pakistan, and Egypt. The unsupervised approaches (TED, SSCD) consistently outperform the weakly supervised alternative. TED with SatMAE achieves the highest exact-month recall (55% at m=0), while TED with GeoRSCLIP, CLIP, or Satlas-Pretrain reaches 92.5% within a three-month tolerance (m=3). Handcrafted features remain competitive for exact-month detection under weak supervision. Our directional margin analysis reveals systematic temporal biases: SSCD paired with GeoRSCLIP or Prithvi-EO-2.0 exhibits the strongest early-warning profile, detecting anomalies before the recorded event, while TED favors confirmation-oriented detection after a change has materialized. These results show that satellite imagery combined with foundation-model embeddings enables scalable, decision-relevant heritage monitoring. Code: https://github.com/microsoft/WATCH

cs.CV↗

arXiv2026

RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design

We introduce RosettaSearch, an inference-time multi-objective optimization approach for backbone conditioned protein sequence design. We use large language models (LLMs) as a generative optimizer within a search algorithm capable of controlled exploration and exploitation, using rewards computed from RosettaFold3, a structure prediction model, under a strict computational budget. In a large-scale evaluation, we apply RosettaSearch to 400 suboptimal sequences generated by LigandMPNN (a state-of-the-art model trained for protein sequence design), recovering high-fidelity designs that LigandMPNN's single-pass decoding fails to produce. RosettaSearch's designs show improvements in structural fidelity metrics ranging between 18% to 68%, translating to a 2.5x improvement in design success rate. We observe that these gains in success rate are robust when RosettaSearch-designed sequences are evaluated with an independent structure prediction oracle (Chai-1) and generalize across two distinct LLM families (o4-mini and Gemini-3), with performance scaling consistently with reasoning capability. We further demonstrate that RosettaSearch improves the sequence fidelity of ProteinMPNN designs for de novo backbones from the Dayhoff atlas, showing that the approach generalizes beyond native protein structures to computationally generated backbones. We also demonstrate a multi-modal extension of RosettaSearch with vision-language models, where images of predicted protein structures are used as feedback to incorporate structural context to guide protein sequence generation. To our knowledge, this is the first large-scale demonstration that LLMs can serve as effective generative optimizers for backbone-conditioned protein sequence design, yielding systematic gains without any model retraining.

cs.LG↗

arXiv2026

GeoAI Agency Primitives

We present ongoing research on agency primitives for GeoAI assistants -- core capabilities that connect Foundation models to the artifact-centric, human-in-the-loop workflows where GIS practitioners actually work. Despite advances in satellite image captioning, visual question answering, and promptable segmentation, these capabilities have not translated into productivity gains for practitioners who spend most of their time producing vector layers, raster maps, and cartographic products. The gap is not model capability alone but the absence of an agency layer that supports iterative collaboration. We propose a vocabulary of $9$ primitives for such a layer -- including navigation, perception, geo-referenced memory, and dual modeling -- along with a benchmark that measures human productivity. Our goal is a vocabulary that makes agentic assistance in GIS implementable, testable, and comparable.

cs.CV↗

arXiv2026

Satellite-Based Detection of Looted Archaeological Sites Using Machine Learning

Looting at archaeological sites poses a severe risk to cultural heritage, yet monitoring thousands of remote locations remains operationally difficult. We present a scalable and satellite-based pipeline to detect looted archaeological sites, using PlanetScope monthly mosaics (4.7m/pixel) and a curated dataset of 1,943 archaeological sites in Afghanistan (898 looted, 1,045 preserved) with multi-year imagery (2016--2023) and site-footprint masks. We compare (i) end-to-end CNN classifiers trained on raw RGB patches and (ii) traditional machine learning (ML) trained on handcrafted spectral/texture features and embeddings from recent remote-sensing foundation models. Results indicate that ImageNet-pretrained CNNs combined with spatial masking reach an F1 score of 0.926, clearly surpassing the strongest traditional ML setup, which attains an F1 score of 0.710 using SatCLIP-V+RF+Mean, i.e., location and vision embeddings fed into a Random Forest with mean-based temporal aggregation. Ablation studies demonstrate that ImageNet pretraining (even in the presence of domain shift) and spatial masking enhance performance. In contrast, geospatial foundation model embeddings perform competitively with handcrafted features, suggesting that looting signatures are extremely localized. The repository is available at https://github.com/microsoft/looted_site_detection.

cs.CV↗

arXiv2026

BYOL: Bring Your Own Language Into LLMs

Large Language Models (LLMs) exhibit strong multilingual capabilities, yet remain fundamentally constrained by the severe imbalance in global language resources. While over 7,000 languages are spoken worldwide, only a small subset (fewer than 100) has sufficient digital presence to meaningfully influence modern LLM training. This disparity leads to systematic underperformance, cultural misalignment, and limited accessibility for speakers of low-resource and extreme-low-resource languages. To address this gap, we introduce Bring Your Own Language (BYOL), a unified framework for scalable, language-aware LLM development tailored to each language's digital footprint. BYOL begins with a language resource classification that maps languages into four tiers (Extreme-Low, Low, Mid, High) using curated web-scale corpora, and uses this classification to select the appropriate integration pathway. For low-resource languages, we propose a full-stack data refinement and expansion pipeline that combines corpus cleaning, synthetic text generation, continual pretraining, and supervised finetuning. Applied to Chichewa and Maori, this pipeline yields language-specific LLMs that achieve approximately 12 percent average improvement over strong multilingual baselines across 12 benchmarks, while preserving English and multilingual capabilities via weight-space model merging. For extreme-low-resource languages, we introduce a translation-mediated inclusion pathway, and show on Inuktitut that a tailored machine translation system improves over a commercial baseline by 4 BLEU, enabling high-accuracy LLM access when direct language modeling is infeasible. Finally, we release human-translated versions of the Global MMLU-Lite benchmark in Chichewa, Maori, and Inuktitut, and make our codebase and models publicly available at https://github.com/microsoft/byol .

cs.CL↗

arXiv2025

AI Diffusion in Low Resource Language Countries

Artificial intelligence (AI) is diffusing globally at unprecedented speed, but adoption remains uneven. Frontier Large Language Models (LLMs) are known to perform poorly on low-resource languages due to data scarcity. We hypothesize that this performance deficit reduces the utility of AI, thereby slowing adoption in Low-Resource Language Countries (LRLCs). To test this, we use a weighted regression model to isolate the language effect from socioeconomic and demographic factors, finding that LRLCs have a share of AI users that is approximately 20% lower relative to their baseline. These results indicate that linguistic accessibility is a significant, independent barrier to equitable AI diffusion.

cs.CL↗

arXiv2025

Measuring AI Diffusion: A Population-Normalized Metric for Tracking Global AI Usage

Measuring global AI diffusion remains challenging due to a lack of population-normalized, cross-country usage data. We introduce AI User Share, a novel indicator that estimates the share of each country's working-age population actively using AI tools. Built from anonymized Microsoft telemetry and adjusted for device access and mobile scaling, this metric spans 147 economies and provides consistent, real-time insight into global AI diffusion. We find wide variation in adoption, with a strong correlation between AI User Share and GDP. High uptake is concentrated in developed economies, though usage among internet-connected populations in lower-income countries reveals substantial latent demand. We also detect sharp increases in usage following major product launches, such as DeepSeek in early 2025. While the metric's reliance solely on Microsoft telemetry introduces potential biases related to this user base, it offers an important new lens into how AI is spreading globally. AI User Share enables timely benchmarking that can inform data-driven AI policy.

cs.CY↗

arXiv2025

Towards reliable use of artificial intelligence to classify otitis media using otoscopic images: Addressing bias and improving data quality

Ear disease contributes significantly to global hearing loss, with recurrent otitis media being a primary preventable cause in children, impacting development. Artificial intelligence (AI) offers promise for early diagnosis via otoscopic image analysis, but dataset biases and inconsistencies limit model generalizability and reliability. This retrospective study systematically evaluated three public otoscopic image datasets (Chile; Ohio, USA; Türkiye) using quantitative and qualitative methods. Two counterfactual experiments were performed: (1) obscuring clinically relevant features to assess model reliance on non-clinical artifacts, and (2) evaluating the impact of hue, saturation, and value on diagnostic outcomes. Quantitative analysis revealed significant biases in the Chile and Ohio, USA datasets. Counterfactual Experiment I found high internal performance (AUC > 0.90) but poor external generalization, because of dataset-specific artifacts. The Türkiye dataset had fewer biases, with AUC decreasing from 0.86 to 0.65 as masking increased, suggesting higher reliance on clinically meaningful features. Counterfactual Experiment II identified common artifacts in the Chile and Ohio, USA datasets. A logistic regression model trained on clinically irrelevant features from the Chile dataset achieved high internal (AUC = 0.89) and external (Ohio, USA: AUC = 0.87) performance. Qualitative analysis identified redundancy in all the datasets and stylistic biases in the Ohio, USA dataset that correlated with clinical outcomes. In summary, dataset biases significantly compromise reliability and generalizability of AI-based otoscopic diagnostic models. Addressing these biases through standardized imaging protocols, diverse dataset inclusion, and improved labeling methods is crucial for developing robust AI solutions, improving high-quality healthcare access, and enhancing diagnostic accuracy.

cs.CY↗

arXiv2025

How good are humans at detecting AI-generated images? Learnings from an experiment

As AI-powered image generation improves, a key question is how well human beings can differentiate between "real" and AI-generated or modified images. Using data collected from the online game "Real or Not Quiz.", this study investigates how effectively people can distinguish AI-generated images from real ones. Participants viewed a randomized set of real and AI-generated images, aiming to identify their authenticity. Analysis of approximately 287,000 image evaluations by over 12,500 global participants revealed an overall success rate of only 62\%, indicating a modest ability, slightly above chance. Participants were most accurate with human portraits but struggled significantly with natural and urban landscapes. These results highlight the inherent challenge humans face in distinguishing AI-generated visual content, particularly images without obvious artifacts or stylistic cues. This study stresses the need for transparency tools, such as watermarks and robust AI detection tools to mitigate the risks of misinformation arising from AI-generated content

cs.HC↗

arXiv2023

Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images

Due to deteriorating environmental conditions and increasing human activity, conservation efforts directed towards wildlife is crucial. Motion-activated camera traps constitute an efficient tool for tracking and monitoring wildlife populations across the globe. Supervised learning techniques have been successfully deployed to analyze such imagery, however training such techniques requires annotations from experts. Reducing the reliance on costly labelled data therefore has immense potential in developing large-scale wildlife tracking solutions with markedly less human labor. In this work we propose WildMatch, a novel zero-shot species classification framework that leverages multimodal foundation models. In particular, we instruction tune vision-language models to generate detailed visual descriptions of camera trap images using similar terminology to experts. Then, we match the generated caption to an external knowledge base of descriptions in order to determine the species in a zero-shot manner. We investigate techniques to build instruction tuning datasets for detailed animal description generation and propose a novel knowledge augmentation technique to enhance caption quality. We demonstrate the performance of WildMatch on a new camera trap dataset collected in the Magdalena Medio region of Colombia.

cs.CV↗

arXiv2023

Assessment of Differentially Private Synthetic Data for Utility and Fairness in End-to-End Machine Learning Pipelines for Tabular Data

Differentially private (DP) synthetic data sets are a solution for sharing data while preserving the privacy of individual data providers. Understanding the effects of utilizing DP synthetic data in end-to-end machine learning pipelines impacts areas such as health care and humanitarian action, where data is scarce and regulated by restrictive privacy laws. In this work, we investigate the extent to which synthetic data can replace real, tabular data in machine learning pipelines and identify the most effective synthetic data generation techniques for training and evaluating machine learning models. We investigate the impacts of differentially private synthetic data on downstream classification tasks from the point of view of utility as well as fairness. Our analysis is comprehensive and includes representatives of the two main types of synthetic data generation algorithms: marginal-based and GAN-based. To the best of our knowledge, our work is the first that: (i) proposes a training and evaluation framework that does not assume that real data is available for testing the utility and fairness of machine learning models trained on synthetic data; (ii) presents the most extensive analysis of synthetic data set generation algorithms in terms of utility and fairness when used for training machine learning models; and (iii) encompasses several different definitions of fairness. Our findings demonstrate that marginal-based synthetic data generators surpass GAN-based ones regarding model training utility for tabular data. Indeed, we show that models trained using data generated by marginal-based algorithms can exhibit similar utility to models trained using real data. Our analysis also reveals that the marginal-based synthetic data generator MWEM PGM can train models that simultaneously achieve utility and fairness characteristics close to those obtained by models trained with real data.

cs.LG↗

arXiv2023

Poverty rate prediction using multi-modal survey and earth observation data

This work presents an approach for combining household demographic and living standards survey questions with features derived from satellite imagery to predict the poverty rate of a region. Our approach utilizes visual features obtained from a single-step featurization method applied to freely available 10m/px Sentinel-2 surface reflectance satellite imagery. These visual features are combined with ten survey questions in a proxy means test (PMT) to estimate whether a household is below the poverty line. We show that the inclusion of visual features reduces the mean error in poverty rate estimates from 4.09% to 3.88% over a nationally representative out-of-sample test set. In addition to including satellite imagery features in proxy means tests, we propose an approach for selecting a subset of survey questions that are complementary to the visual features extracted from satellite imagery. Specifically, we design a survey variable selection approach guided by the full survey and image features and use the approach to determine the most relevant set of small survey questions to include in a PMT. We validate the choice of small survey questions in a downstream task of predicting the poverty rate using the small set of questions. This approach results in the best performance -- errors in poverty rate decrease from 4.09% to 3.71%. We show that extracted visual features encode geographic and urbanization differences between regions.

cs.LG↗

arXiv2023

How effective is multifactor authentication at deterring cyberattacks?

This study investigates the effectiveness of multifactor authentication (MFA) in protecting commercial accounts from unauthorized access, with an additional focus on accounts with known credential leaks. We employ the benchmark-multiplier method, coupled with manual account review, to evaluate the security performance of various MFA methods in a large dataset of Microsoft Azure Active Directory users exhibiting suspicious activity. Our findings reveal that MFA implementation offers outstanding protection, with over 99.99% of MFA-enabled accounts remaining secure during the investigation period. Moreover, MFA reduces the risk of compromise by 99.22% across the entire population and by 98.56% in cases of leaked credentials. We further demonstrate that dedicated MFA applications, such as Microsoft Authenticator, outperform SMS-based authentication, though both methods provide significantly enhanced security compared to not using MFA. Based on these results, we strongly advocate for the default implementation of MFA in commercial accounts to increase security and mitigate unauthorized access risks.

cs.CR↗

arXiv2022

Dwelling Type Classification for Disaster Risk Assessment Using Satellite Imagery

Vulnerability and risk assessment of neighborhoods is essential for effective disaster preparedness. Existing traditional systems, due to dependency on time-consuming and cost-intensive field surveying, do not provide a scalable way to decipher warnings and assess the precise extent of the risk at a hyper-local level. In this work, machine learning was used to automate the process of identifying dwellings and their type to build a potentially more effective disaster vulnerability assessment system. First, satellite imageries of low-income settlements and vulnerable areas in India were used to identify 7 different dwelling types. Specifically, we formulated the dwelling type classification as a semantic segmentation task and trained a U-net based neural network model, namely TernausNet, with the data we collected. Then a risk score assessment model was employed, using the determined dwelling type along with an inundation model of the regions. The entire pipeline was deployed to multiple locations prior to natural hazards in India in 2020. Post hoc ground-truth data from those regions was collected to validate the efficacy of this model which showed promising performance. This work can aid disaster response organizations and communities at risk by providing household-level risk information that can inform preemptive actions.

cs.LG↗

arXiv2022

MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models

Generative machine learning models are being increasingly viewed as a way to share sensitive data between institutions. While there has been work on developing differentially private generative modeling approaches, these approaches generally lead to sub-par sample quality, limiting their use in real world applications. Another line of work has focused on developing generative models which lead to higher quality samples but currently lack any formal privacy guarantees. In this work, we propose the first formal framework for membership privacy estimation in generative models. We formulate the membership privacy risk as a statistical divergence between training samples and hold-out samples, and propose sample-based methods to estimate this divergence. Compared to previous works, our framework makes more realistic and flexible assumptions. First, we offer a generalizable metric as an alternative to the accuracy metric especially for imbalanced datasets. Second, we loosen the assumption of having full access to the underlying distribution from previous studies , and propose sample-based estimations with theoretical guarantees. Third, along with the population-level membership privacy risk estimation via the optimal membership advantage, we offer the individual-level estimation via the individual privacy risk. Fourth, our framework allows adversaries to access the trained model via a customized query, while prior works require specific attributes.

cs.CR↗

arXiv2022

An Artificial Intelligence Dataset for Solar Energy Locations in India

Rapid development of renewable energy sources, particularly solar photovoltaics (PV), is critical to mitigate climate change. As a result, India has set ambitious goals to install 500 gigawatts of solar energy capacity by 2030. Given the large footprint projected to meet renewables energy targets, the potential for land use conflicts over environmental values is high. To expedite development of solar energy, land use planners will need access to up-to-date and accurate geo-spatial information of PV infrastructure. In this work, we developed a spatially explicit machine learning model to map utility-scale solar projects across India using freely available satellite imagery with a mean accuracy of 92%. Our model predictions were validated by human experts to obtain a dataset of 1363 solar PV farms. Using this dataset, we measure the solar footprint across India and quantified the degree of landcover modification associated with the development of PV infrastructure. Our analysis indicates that over 74% of solar development In India was built on landcover types that have natural ecosystem preservation, or agricultural value.

cs.LG↗