Showing 1–50 of 161 results for author: Oliveira, D

A Conceptual Framework for Refining Influence Knowledge from Simulation Evidence in Cyber-Physical Systems

Authors: Barbara da Silva Oliveira, Julien Deantoni, Nicolas Ferry

Abstract: Cyber-physical systems (CPS) are typically developed by multiple stakeholders who produce artefacts tailored to their specific domains of expertise. The behaviour of these systems emerges from the interaction between those artefacts and their operational environment. Simulation and co-simulation have become essential approaches for analysing CPS behaviour and, through simulation campaigns, develop… ▽ More Cyber-physical systems (CPS) are typically developed by multiple stakeholders who produce artefacts tailored to their specific domains of expertise. The behaviour of these systems emerges from the interaction between those artefacts and their operational environment. Simulation and co-simulation have become essential approaches for analysing CPS behaviour and, through simulation campaigns, developers can explore system responses under changing conditions, including interactions with the environment. However, the lack of details and understanding of some environmentmediated interactions (typically the ones beyond direct sensing and actuation), which remain unmodelled due to their complexity, a lack of time, or a lack of domain experience, hinders the proper comprehension and exploitation of simulation results. To address these limitations, we propose a conceptual framework leveraging the novel concept of Influences to support the iterative and incremental refinement of simulation campaigns and deepen the understanding of the system behaviour. We demonstrate the proposed approach through a case study involving a mobile robot implemented using Simulink/Gazebo co-simulation. △ Less

Submitted 22 July, 2026; originally announced August 2026.

Journal ref: ACM/IEEE 29th International Conference on Model Driven Engineering Languages and Systems, Oct 2026, Malaga, Spain

Crowd-Sourced Geographies of Income: Using Google Maps Points of Interest as High-Frequency Proxies for Sub-Municipal Income Estimation in Sao Paulo, Brazil

Authors: Adrienne C. Kinney, Anya Workman, Ademar Takeo Akabane, Jenna Barac, Paulo Fernando Braga Carvalho, Jeova Farias, Fernando Nascimento, Paulo Ricardo da Silva Oliveira

Abstract: Accurate, up-to-date income data at the sub-municipal scale is essential for social policy in middle-income countries, yet in Brazil it depends on a costly decennial census whose intercensal gap recently exceeded a decade. We test whether the composition of crowd-sourced Google Maps Points of Interest (POIs) can serve as a high-frequency, low-cost proxy for household income across the 26,625 censu… ▽ More Accurate, up-to-date income data at the sub-municipal scale is essential for social policy in middle-income countries, yet in Brazil it depends on a costly decennial census whose intercensal gap recently exceeded a decade. We test whether the composition of crowd-sourced Google Maps Points of Interest (POIs) can serve as a high-frequency, low-cost proxy for household income across the 26,625 census sectors of the municipality of Sao Paulo. Using a theoretically motivated set of POI categories retrieved from Google Places, we represent each sector by its POI counts, decompose these high-dimensional, sparse features with principal component analysis (PCA) and non-negative matrix factorization (NMF), and train a sweep of regression models to predict census-derived income. Under a data leakage-aware spatial validation design the best model (NMF with gradient boosting) attains a held-out R^2 of 0.65, with performance stable across feature-extraction methods. Interpretable decompositions reveal which POI types carry the income signal. These results suggest that commercial, crowd-sourced geospatial data can complement conventional income statistics during intercensal periods, and we discuss extensions toward multidimensional poverty and the capabilities framework. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Bidirectional Typing with Freezing, Skeletons, and Ghosts

Authors: Wenhao Tang, Shengyi Jiang, Aghilas Y. Boussaa, Sam Lindley, Bruno C. d. S. Oliveira

Abstract: Bidirectional typing makes use of local information flow between functions and arguments. Conventional bidirectional typing only supports unidirectional information flow, typically from functions to arguments, which is insufficient to infer first-class polymorphism. Existing work on improving information flow either has limited support for mixed information flow or requires ad hoc mechanisms that… ▽ More Bidirectional typing makes use of local information flow between functions and arguments. Conventional bidirectional typing only supports unidirectional information flow, typically from functions to arguments, which is insufficient to infer first-class polymorphism. Existing work on improving information flow either has limited support for mixed information flow or requires ad hoc mechanisms that harm predictability. We propose Fresco, a novel bidirectional type inference approach to first-class polymorphism. Fresco enables local type information to flow back and forth between functions and arguments via skeletons, with ghosts representing unknown type information, and allows users to customise the direction of information flow by freezing. The flexible information flow of Fresco enables expressive and predictable inference for first-class polymorphism. We provide a declarative specification for Fresco, a simple type inference algorithm that is sound and complete with respect to the declarative system, and a prototype implementation that further generalises Fresco to infer modal effect types. △ Less

Submitted 17 July, 2026; originally announced July 2026.

Economic Transformation and Cultural Change: Evidence from Two Centuries of French Drama

Authors: T. D. Oliveira, L. A. Attilio, M. J. Davila-Fernandez

Abstract: How do large-scale economic transformations shape cultural production? We address this question by combining computational linguistics, econometrics, and formal modelling, using French drama as a well-documented empirical laboratory. Applying latent Dirichlet allocation to a corpus of 1,215 theatrical texts published between 1700 and 1900, we show that aristocratic discourse centred on sovereignty… ▽ More How do large-scale economic transformations shape cultural production? We address this question by combining computational linguistics, econometrics, and formal modelling, using French drama as a well-documented empirical laboratory. Applying latent Dirichlet allocation to a corpus of 1,215 theatrical texts published between 1700 and 1900, we show that aristocratic discourse centred on sovereignty and political authority was gradually displaced by bourgeois and household economic themes as French capitalism developed. Bayesian vector autoregressive models with max-share shock identification suggest a temporal shift in the literary response to economic shocks: bourgeois everyday-life themes reacted to GDP shocks in the eighteenth century, whereas household-economic concerns became responsive only after 1820, amid accelerating industrialisation. A discrete-choice model shows that peer effects among authors and sensitivity to prevailing economic conditions can jointly account for these dynamics. Monte Carlo simulations reproduce the observed historical trajectory with reasonable fidelity. These findings offer a quantitative framework for understanding how economic transformations propagate into cultural production through identifiable social mechanisms, contributing to the study of cultural evolution and the long-run relationship between institutions and literary discourse. △ Less

Submitted 19 June, 2026; originally announced June 2026.

How Much Do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations

Authors: Eduardo Ferreira da Silva, Mayki dos Santos Oliveira, Joel Machado Pires Denis Dantas Boaventura, Frederico Araújo Durão

Abstract: Incorporating textual reviews into a Recommender System has become a prominent strategy for enriching collaborative signals with semantic information. However, the actual contribution of review-derived representations remains an open question, particularly when strong collaborative baselines are employed. In this work, we systematically investigate the impact of textual information on Matrix Facto… ▽ More Incorporating textual reviews into a Recommender System has become a prominent strategy for enriching collaborative signals with semantic information. However, the actual contribution of review-derived representations remains an open question, particularly when strong collaborative baselines are employed. In this work, we systematically investigate the impact of textual information on Matrix Factorization by introducing and comparing three enrichment strategies over a common collaborative backbone. First, we propose a learnable gating mechanism that adaptively balances collaborative and textual signals during training. This mechanism is applied to two distinct review representations: (i) aggregated topic profiles extracted from user and item histories, and (ii) full text embedding representations derived from reviews. Additionally, we explore a cross-attention mechanism that identifies and emphasizes the most informative dimensions of the textual representation before fusion with collaborative factors. We evaluate six variants: pure, enriched with topic profiles and text via gating; enriched with topics and text via gating; and enhanced with cross-attention over textual features. Experiments across multiple review-based datasets reveal that although adaptive fusion mechanisms improve representation flexibility, the marginal contribution of textual signals remains limited compared to the collaborative backbone. These findings suggest that, under typical rating-prediction settings, collaborative information continues to dominate performance, raising important considerations for the effective integration of semantic review signals into recommendation models. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: 14 pages, 4 figures, SBBD 2026 ISSN 2763-8979

Fortress: A Case Study in Stabilizing Search Recommendations via Temporal Data Augmentation and Feature Pruning

Authors: Milind Pandurang Jagre, Jia Huang, Dayvid V. R. Oliveira, Zhinan Cheng, Babak Seyed Aghazadeh, Puja Das, Chris Alvino, Jinda Han, Kailash Thiyagarajan

Abstract: In search and recommendation systems, predictive models often suffer from temporal instability when certain input features introduce volatility in output scores. This instability can degrade model reliability and user experience especially in multi-stage systems where consistent predictions are critical for downstream decision making. We introduce Fortress, a general framework for enhancing model… ▽ More In search and recommendation systems, predictive models often suffer from temporal instability when certain input features introduce volatility in output scores. This instability can degrade model reliability and user experience especially in multi-stage systems where consistent predictions are critical for downstream decision making. We introduce Fortress, a general framework for enhancing model stability and accuracy by identifying and pruning features that contribute to inconsistent prediction scores over time. Fortress leverages historical snapshots temporally partitioned datasets capturing score fluctuations for the same entity across periods and follows a four-step process: (1) collect historical snapshots, (2) identify samples with unstable predictions, (3) isolate and remove instability-inducing features, and (4) retrain models using only stable features. While semantic features from LLMs and BERT-based models improve generalization, they often lack full query or entity coverage. Engagement-based features offer strong predictive power but tend to introduce temporal instability. Fortress mitigates this trade-off by suppressing the volatility of engagement signals while retaining their predictive value leading to more stable and accurate models. We validate Fortress on a query-to-app relevance model in a large-scale app marketplace. Offline experiments demonstrate notable improvements in prediction stability (measured by Coefficient of Variation) and classification performance (measured by PR-AUC). △ Less

Submitted 14 May, 2026; originally announced May 2026.

State Canonization and Early Pruning in Width-Based Automated Theorem Proving

Authors: Mateus de Oliveira Oliveira, Sam Urmian

Abstract: Width-based automated theorem proving is a framework where counterexamples to graph-theoretic conjectures are searched width-wise relative to some graph width measure, such as treewidth or pathwidth. In a recent work it has been shown that dynamic programming algorithms operating on tree decompositions can be combined together with the purpose of width-based theorem proving. This approach can be… ▽ More Width-based automated theorem proving is a framework where counterexamples to graph-theoretic conjectures are searched width-wise relative to some graph width measure, such as treewidth or pathwidth. In a recent work it has been shown that dynamic programming algorithms operating on tree decompositions can be combined together with the purpose of width-based theorem proving. This approach can be used to show that several long-standing conjectures in graph theory can be tested in time \(2^{2^{k^{O(1)}}}\) on the class of graphs of treewidth at most \(k\). In this work, we give the first steps towards evaluating the viability of this framework from a practical standpoint. At the same time, we advance the framework in two directions. First, we introduce a state-canonization technique that significantly reduces the number of states evaluated during the search for a counterexample of the conjecture. Second, we introduce an early-pruning technique that can be applied in the study of conjectures of the form \(\mathcal{P}_1 \rightarrow \mathcal{P}_2\), for graph properties \(\mathcal{P}_1\) and \(\mathcal{P}_2\), where \(\mathcal{P}_1\) is a property closed under subgraphs. As a concrete application, we use our framework in the study of graph-theoretic conjectures related to coloring triangle-free graphs. In particular, our algorithm is able to show that Reed's conjecture for triangle-free graphs is valid on the class of graphs of pathwidth at most 5, and on graphs of treewidth at most 3. Perhaps more interestingly, our algorithm is able to construct in a completely automated way counterexamples to invalid strengthenings of Reed's conjecture. These are the first results showing that width-based automated theorem proving is a promising avenue in the study of graph-theoretic conjectures. △ Less

Submitted 10 May, 2026; originally announced May 2026.

Comments: Full version. 66 pages, 2 figures, 10 tables

MSC Class: 05C15; 05C85; 68R10; 68V15 ACM Class: G.2.2; F.2.2; I.2.3

DALPHIN: Benchmarking Digital Pathology AI Copilots Against Pathologists on an Open Multicentric Dataset

Authors: Carlijn Lems, Sander Moonemans, Natálie Klubíčková, Biagio Brattoli, Taebum Lee, Seokhwi Kim, Veronica Vilaplana, Laura Pons, Sapir Hochman, Mauricio Eduardo Suárez-Franck, Pedro Luis Fernandez, Julius Drachneris, Donatas Petroska, Renaldas Augulis, Arvydas Laurinavicius, Domingos Oliveira, Diana Montezuma, Anouk B. Bouwmeester, Dominique van Midden, Anne-Marie Vos, Shoko Vos, Jolique van Ipenburg, Maschenka Balkenhol, Koen Winkler, Iris Nagtegaal , et al. (31 additional authors not shown)

Abstract: Foundation models with visual question answering capabilities for digital pathology are emerging. Such unprecedented technology requires independent benchmarking to assess its potential in assisting pathologists in routine diagnostics. We created DALPHIN, the first multicentric open benchmark for pathology AI copilots, comprising 1236 images from 300 cases, spanning 130 rare to common diagnoses, 6… ▽ More Foundation models with visual question answering capabilities for digital pathology are emerging. Such unprecedented technology requires independent benchmarking to assess its potential in assisting pathologists in routine diagnostics. We created DALPHIN, the first multicentric open benchmark for pathology AI copilots, comprising 1236 images from 300 cases, spanning 130 rare to common diagnoses, 6 countries, and 14 subspecialties. The DALPHIN design and dataset are introduced alongside a human performance benchmark of 31 pathologists from 10 countries with varying expertise. We report results for two general-purpose (GPT-5, Gemini 2.5 Pro) and one pathology-specific copilot (PathChat+) for sequential and independent answer generation. We observed no statistically significant difference from expert-level performance in four of six tasks for PathChat, 2/6 tasks for Gemini, and 1/6 tasks for GPT. DALPHIN is publicly released with sequestered, indirectly accessible ground truth to foster robust and enduring benchmarking. Data, methods, and the evaluation platform are accessible through dalphin.grand-challenge.org. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Comments: Our dataset is available at https://zenodo.org/records/18609450 , our code is available at https://github.com/computationalpathologygroup/DALPHIN , and our benchmark is available at https://dalphin.grand-challenge.org/

A Gated Hybrid Contrastive Collaborative Filtering Recommendation

Authors: Eduardo Ferreira da Silva, Mayki dos Santos Oliveira, Joel Machado Pires, Denis Dantas Boaventura, Maycon Maciel Peixoto, Cassio Serafim Prazeres, Gustavo Bittencourt Figueiredo, Miriam Capretz, Frederico Araujo Durão

Abstract: Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking quality. This misalignment limits their effectiveness in top-N recommendation scenarios, where discriminative ranking is essential. To address this gap, we propose a Gated Hybrid Collaborative Filtering fr… ▽ More Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking quality. This misalignment limits their effectiveness in top-N recommendation scenarios, where discriminative ranking is essential. To address this gap, we propose a Gated Hybrid Collaborative Filtering framework that integrates review-derived representations into an autoencoder-based collaborative model. The architecture injects semantic signals layer-wise through an adaptive gating mechanism that dynamically balances collaborative embeddings and topic-based features during encoding. To further refine the latent space, we introduce a contrastive learning module that aligns semantic and collaborative signals. We evaluate the framework across five distinct configurations: Pure collaborative; Topic and Gated; Text and Gated; and the addition of contrastive objectives (Contrastive and Topic, and Contrastive and Text). To explicitly optimize ranking behavior, the model is trained with a pairwise Bayesian personalized ranking objective, which promotes separation between relevant and non-relevant items in the latent space. Experiments on Amazon Movies & TV, IMDb, and Rotten Tomatoes demonstrate consistent improvements in hit rate @10 and normalized discounted cumulative gain @10 over state-of-the-art review-aware baselines. Results highlight the importance of controlled semantic fusion for ranking-driven recommendation. △ Less

Submitted 29 April, 2026; originally announced April 2026.

Deep Clustering for Climate: Analyzing Teleconnections through Learned Categorical States

Authors: Lívia Meinhardt, Dário Oliveira

Abstract: Understanding and representing complex climate variability is essential for both scientific analysis and predictive modeling. However, identifying meaningful climate regimes from raw variables is challenging, as they exhibit high noise and nonlinear dependencies. In this work, we explore the use of Masked Siamese Networks to discretize climate time series into semantically rich clusters. Focusing… ▽ More Understanding and representing complex climate variability is essential for both scientific analysis and predictive modeling. However, identifying meaningful climate regimes from raw variables is challenging, as they exhibit high noise and nonlinear dependencies. In this work, we explore the use of Masked Siamese Networks to discretize climate time series into semantically rich clusters. Focusing on daily minimum and maximum temperature, we show that the resulting representations: (i) yield clusters that reflect meaningful climate states under our modeling assumptions, offering a simplified representation for downstream use; (ii) enable sampling and analysis of specific climate scenarios; and (iii) exhibit statistical associations with El Niño events, underscoring their scientific relevance. Our findings highlight the potential of self-supervised discretization as a tool for climate data analysis and open avenues for incorporating richer climate indicators in future work. △ Less

Submitted 24 April, 2026; originally announced April 2026.

Autark: A Serverless Toolkit for Prototyping Urban Visual Analytics Systems

Authors: Lucas Alexandre, João Rulff, Talisson Souza, Gustavo Moreira, Daniel de Oliveira, Claudio Silva, Fabio Miranda, Marcos Lage

Abstract: The development of visual analytics (VA) systems has traditionally been a labor-intensive process, balancing design methodologies with complex software engineering practices. In domain-specific fields like urban VA, this challenge is amplified by heterogeneous data streams and a reliance on complex, multi-service architectures that hinder fast development, deployment, and reproducibility. Despite… ▽ More The development of visual analytics (VA) systems has traditionally been a labor-intensive process, balancing design methodologies with complex software engineering practices. In domain-specific fields like urban VA, this challenge is amplified by heterogeneous data streams and a reliance on complex, multi-service architectures that hinder fast development, deployment, and reproducibility. Despite the richness of the urban VA literature, the field lacks a consolidated toolkit that encapsulates the core components of these systems, such as spatial data management, analytical processing, and visualization, into a unified, lightweight framework. In this paper, we introduce Autark, a serverless toolkit designed for the rapid prototyping of urban VA systems. Autark provides domain-aware abstractions through a self-contained architecture, enabling researchers to transition from design intention to deployed, shareable systems within hours. Furthermore, Autark's structured, tightly scoped interfaces make it well-suited for AI-assisted coding workflows, where LLMs produce more reliable code when composing from well-defined abstractions rather than generating complex solutions from scratch. Our contributions are: (1) the Autark toolkit, a serverless architecture for rapid prototyping of urban VA; (2) a comparative study of LLM coding effectiveness with and without Autark; and (3) a series of usage scenarios demonstrating its capability to streamline the creation of robust, shareable urban VA prototypes. Autark is available at https://autarkjs.org/. △ Less

Submitted 22 April, 2026; originally announced April 2026.

Comments: Autark is available at https://autarkjs.org/

DharmaOCR: Specialized Small Language Models for Structured OCR that outperform Open-Source and Commercial Baselines

Authors: Gabriel Pimenta de Freitas Cardoso, Caio Lucas da Silva Chacon, Jonas Felipe da Fonseca Oliveira, Paulo Henrique de Medeiros Araujo

Abstract: This manuscript introduces DharmaOCR Full and Lite, a pair of specialized small language models (SSLMs) for structured OCR that jointly optimize transcription quality, generation stability, and inference cost. It also presents DharmaOCR-Benchmark, a benchmark that covers printed, handwritten, and legal/administrative documents, and proposes a unified evaluation protocol that measures fidelity and… ▽ More This manuscript introduces DharmaOCR Full and Lite, a pair of specialized small language models (SSLMs) for structured OCR that jointly optimize transcription quality, generation stability, and inference cost. It also presents DharmaOCR-Benchmark, a benchmark that covers printed, handwritten, and legal/administrative documents, and proposes a unified evaluation protocol that measures fidelity and structure while explicitly tracking text degeneration as a first-class benchmark metric (alongside unit cost). Beyond reporting degeneration rates, the manuscript empirically shows degeneration is not merely a quality failure, since it materially worsens production performance by increasing response time, reducing throughput, and inflating computational cost due to abnormally long generations. To the best of the author's knowledge, as a methodological contribution, this is the first application of Direct Preference Optimization (DPO) for OCR, explicitly using degenerate generations as rejected examples to penalize looping behavior. Combined with Supervised Fine-Tuning (SFT) for enforcing a strict JSON schema (header, margin, footer, and text), DPO consistently reduces degeneration rate across model families (up to 87.6% relative) while preserving or improving extraction quality. The resulting models, namely, DharmaOCR Full (7B) and DharmaOCR Lite (3B), set a new state-of-the-art on DharmaOCR-Benchmark, outperforming each open-source and commercial baseline model evaluated regarding extraction quality, reaching 0.925 and 0.911 scores with 0.40% and 0.20% degeneration rates. AWQ quantization reduced up to 22% per-page cost with negligible quality loss, enabling a strong quality-cost trade-off in comparison to proprietary OCR APIs and open-source alternatives. △ Less

Submitted 15 April, 2026; originally announced April 2026.

Solution for 10th Competition on Ambivalence/Hesitancy (AH) Video Recognition Challenge using Divergence-Based Multimodal Fusion

Authors: Aislan Gabriel O. Souza, Agostinho Freire, Leandro Honorato Silva, Igor Lucas B. da Silva, João Vinícius R. de Andrade, Gabriel C. de Albuquerque, Lucas Matheus da S. Oliveira, Mário Stela Guerra, Luciana Machado

Abstract: We address the Ambivalence/Hesitancy (A/H) Video Recognition Challenge at the 10th ABAW Competition (CVPR 2026). We propose a divergence-based multimodal fusion that explicitly measures cross-modal conflict between visual, audio, and textual channels. Visual features are encoded as Action Units (AUs) extracted via Py-Feat, audio via Wav2Vec 2.0, and text via BERT. Each modality is processed by a B… ▽ More We address the Ambivalence/Hesitancy (A/H) Video Recognition Challenge at the 10th ABAW Competition (CVPR 2026). We propose a divergence-based multimodal fusion that explicitly measures cross-modal conflict between visual, audio, and textual channels. Visual features are encoded as Action Units (AUs) extracted via Py-Feat, audio via Wav2Vec 2.0, and text via BERT. Each modality is processed by a BiLSTM with attention pooling and projected into a shared embedding space. The fusion module computes pairwise absolute differences between modality embeddings, directly capturing the incongruence that characterizes A/H. On the BAH dataset, our approach achieves a Macro F1 of 0.6808 on the validation test set, outperforming the challenge baseline of 0.2827. Statistical analysis across 1{,}132 videos confirms that temporal variability of AUs is the dominant visual discriminator of A/H. △ Less

Submitted 15 March, 2026; originally announced March 2026.

StoryMovie: A Dataset for Semantic Alignment of Visual Stories with Movie Scripts and Subtitles

Authors: Daniel Oliveira, David Martins de Matos

Abstract: Visual storytelling models that correctly ground entities in images may still hallucinate semantic relationships, generating incorrect dialogue attribution, character interactions, or emotional states. We introduce StoryMovie, a dataset of 1,757 stories aligned with movie scripts and subtitles through LCS matching. Our alignment pipeline synchronizes screenplay dialogue with subtitle timestamps, e… ▽ More Visual storytelling models that correctly ground entities in images may still hallucinate semantic relationships, generating incorrect dialogue attribution, character interactions, or emotional states. We introduce StoryMovie, a dataset of 1,757 stories aligned with movie scripts and subtitles through LCS matching. Our alignment pipeline synchronizes screenplay dialogue with subtitle timestamps, enabling dialogue attribution by linking character names from scripts to temporal positions from subtitles. Using this aligned content, we generate stories that maintain visual grounding tags while incorporating authentic character names, dialogue, and relationship dynamics. We fine-tune Qwen Storyteller3 on this dataset, building on prior work in visual grounding and entity re-identification. Evaluation using DeepSeek V3 as judge shows that Storyteller3 achieves an 89.9% win rate against base Qwen2.5-VL 7B on subtitle alignment. Compared to Storyteller, trained without script grounding, Storyteller3 achieves 48.5% versus 38.0%, confirming that semantic alignment progressively improves dialogue attribution beyond visual grounding alone. △ Less

Submitted 25 February, 2026; originally announced February 2026.

Comments: 15 pages, submitted to Journal of Visual Communication and Image Representation

ACM Class: I.2.7; I.2.10; I.4.8

Snapping Actuators with Asymmetric and Sequenced Motion

Authors: Xin Li, Ye Jin, Mohsen Jafarpour, Hugo de Souza Oliveira, Edoardo Milana

Abstract: Snapping instabilities in soft structures offer a powerful pathway to achieve rapid and energy-efficient actuation. In this study, an eccentric dome-shaped snapping actuator is developed to generate controllable asymmetric motion through geometry-induced instability. Finite element simulations and experiments reveal consistent asymmetric deformation and the corresponding pressure characteristics.… ▽ More Snapping instabilities in soft structures offer a powerful pathway to achieve rapid and energy-efficient actuation. In this study, an eccentric dome-shaped snapping actuator is developed to generate controllable asymmetric motion through geometry-induced instability. Finite element simulations and experiments reveal consistent asymmetric deformation and the corresponding pressure characteristics. By coupling four snapping actuators in a pneumatic network, a compact quadrupedal robot achieves coordinated wavelike locomotion using only a single pressure input. The robot exhibits frequency-dependent performance with a maximum speed of 72.78~mm/s at 7.5~Hz. These findings demonstrate the potential of asymmetric snapping mechanisms for physically controlled actuation and lay the groundwork for fully untethered and efficient soft robotic systems. △ Less

Submitted 20 February, 2026; originally announced February 2026.

Comments: 9th IEEE-RAS International Conference on Soft Robotics (RoboSoft 2026)

Ori-Sense: origami capacitive sensing for soft robotic applications

Authors: Hugo de Souza Oliveira, Xin Li, Mohsen Jafarpour, Edoardo Milana

Abstract: This work introduces Ori-Sense, a compliant capacitive sensor inspired by the inverted Kresling origami pattern. The device translates torsional deformation into measurable capacitance changes, enabling proprioceptive feedback for soft robotic systems. Using dissolvable-core molding, we fabricated a monolithic silicone structure with embedded conductive TPU electrodes, forming an integrated soft c… ▽ More This work introduces Ori-Sense, a compliant capacitive sensor inspired by the inverted Kresling origami pattern. The device translates torsional deformation into measurable capacitance changes, enabling proprioceptive feedback for soft robotic systems. Using dissolvable-core molding, we fabricated a monolithic silicone structure with embedded conductive TPU electrodes, forming an integrated soft capacitor. Mechanical characterization revealed low stiffness and minimal impedance, with torque values below 0.01 N mm for axial displacements between -15 mm and 15 mm, and up to 0.03 N mm at 30 degrees twist under compression. Finite-element simulations confirmed localized stresses along fold lines and validated the measured torque-rotation response. Electrical tests showed consistent capacitance modulation up to 30%, directly correlated with the twist angle, and maximal sensitivity of S_theta ~ 0.0067 pF/deg at 5 mm of axial deformation. △ Less

Submitted 20 February, 2026; originally announced February 2026.

Comments: 9th IEEE-RAS International Conference on Soft Robotics (RoboSoft 2026)

The French Drama Revolution: Political Economy and Literary Production, 1700-1900

Authors: Thiago Dumont Oliveira

Abstract: This paper investigates the changing nature of French drama between 1700-1900 using Latent Dirichlet Allocation and Jensen-Shannon Divergence. Results indicate that the topical distribution of French drama changed profoundly after the French Revolution, particularly between 1789 and 1850. Bourgeois themes emerged among the most prevalent topics since the late 18th century. To assess the coevolutio… ▽ More This paper investigates the changing nature of French drama between 1700-1900 using Latent Dirichlet Allocation and Jensen-Shannon Divergence. Results indicate that the topical distribution of French drama changed profoundly after the French Revolution, particularly between 1789 and 1850. Bourgeois themes emerged among the most prevalent topics since the late 18th century. To assess the coevolution of drama and economic growth, I plot the yearly prevalence of topics alongside French GDP between 1700-1900, and discuss these changes in light of the political and economic changes prompted by the French Revolution and the industrialization of the country. △ Less

Submitted 31 January, 2026; originally announced February 2026.

A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy

Authors: Pedro H. Barcha Correia, Ryan W. Achjian, Diego E. G. Caetano de Oliveira, Ygor Acacio Maria, Victor Takashi Hayashi, Marcos Lopes, Charles Christian Miers, Marcos A. Simplicio Jr

Abstract: The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs can exploit LLMs, causing data leaks, unauthorized actions, or compromised outputs, for instance. A… ▽ More The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs can exploit LLMs, causing data leaks, unauthorized actions, or compromised outputs, for instance. As both offensive and defensive prompt injection techniques evolve quickly, a structured understanding of mitigation strategies becomes increasingly important. To address that, this work presents the first systematic literature review on prompt injection mitigation strategies, comprehending 88 studies. Building upon NIST's report on adversarial machine learning, this work contributes to the field through several avenues. First, it identifies studies beyond those documented in NIST's report and other academic reviews and surveys. Second, we propose an extension to NIST taxonomy by introducing additional categories of defenses. Third, by adopting NIST's established terminology and taxonomy as a foundation, we promote consistency and enable future researchers to build upon the standardized taxonomy proposed in this work. Finally, we provide a comprehensive catalog of the reviewed prompt injection defenses, documenting their reported quantitative effectiveness across specific LLMs and attack datasets, while also indicating which solutions are open-source and model-agnostic. This catalog, together with the guidelines presented herein, aims to serve as a practical resource for researchers advancing the field of adversarial machine learning and for developers seeking to implement effective defenses in production systems. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Comments: 27 pages, 14 figures, 11 tables, submitted to Elsevier Computer Science Review

Symbolic Functional Decomposition: A Reconfiguration Approach

Authors: Mateus de Oliveira Oliveira, Wim Van den Broeck

Abstract: Functional decomposition is the process of breaking down a function $f$ into a composition $f=g(f_1,\dots,f_k)$ of simpler functions $f_1,\dots,f_k$ belonging to some class $\mathcal{F}$. This fundamental notion can be used to model applications arising in a wide variety of contexts, ranging from machine learning to formal language theory. In this work, we study functional decomposition by leverag… ▽ More Functional decomposition is the process of breaking down a function $f$ into a composition $f=g(f_1,\dots,f_k)$ of simpler functions $f_1,\dots,f_k$ belonging to some class $\mathcal{F}$. This fundamental notion can be used to model applications arising in a wide variety of contexts, ranging from machine learning to formal language theory. In this work, we study functional decomposition by leveraging on the notion of functional reconfiguration. In this setting, constraints are imposed not only on the factor functions $f_1,\dots,f_k$ but also on the intermediate functions arising during the composition process. We introduce a symbolic framework to address functional reconfiguration and decomposition problems. In our framework, functions arising during the reconfiguration process are represented symbolically, using ordered binary decision diagrams (OBDDs). The function $g$ used to specify the reconfiguration process is represented by a Boolean circuit $C$. Finally, the function class $\mathcal{F}$ is represented by a second-order finite automaton $\mathcal{A}$. Our main result states that functional reconfiguration, and hence functional decomposition, can be solved in fixed-parameter linear time when parameterized by the width of the input OBDD, by structural parameters associated with the reconfiguration circuit $C$, and by the size of the second-order finite automaton $\mathcal{A}$. △ Less

Submitted 13 January, 2026; originally announced January 2026.

Optimal Extended Formulations from Optimal Dynamic Programming Algorithms

Authors: Mateus de Oliveira Oliveira, Wim Van den Broeck

Abstract: Vertex Subset Problems (VSPs) are a class of combinatorial optimization problems on graphs where the goal is to find a subset of vertices satisfying a predefined condition. Two prominent approaches for solving VSPs are dynamic programming over tree-like structures, such as tree decompositions or clique decompositions, and linear programming. In this work, we establish a sharp connection between bo… ▽ More Vertex Subset Problems (VSPs) are a class of combinatorial optimization problems on graphs where the goal is to find a subset of vertices satisfying a predefined condition. Two prominent approaches for solving VSPs are dynamic programming over tree-like structures, such as tree decompositions or clique decompositions, and linear programming. In this work, we establish a sharp connection between both approaches by showing that if a vertex-subset problem $Π$ admits a solution-preserving dynamic programming algorithm that produces tables of size at most $α(k,n)$ when processing a tree decomposition of width at most $k$ of an $n$-vertex graph $G$, then the polytope $P_Π(G)$ defined as the convex-hull of solutions of $Π$ in $G$ has extension complexity at most $O(α(k,n)\cdot n)$. Additionally, this upper bound is optimal under the exponential time hypothesis (ETH). On the one hand, our results imply that ETH-optimal solution-preserving dynamic programming algorithms for combinatorial problems yield optimal-size parameterized extended formulations for the solution polytopes associated with instances of these problems. On the other hand, unconditional lower bounds obtained in the realm of the theory of extended formulations yield unconditional lower bounds on the table complexity of solution-preserving dynamic programming algorithms. △ Less

Submitted 13 January, 2026; v1 submitted 11 January, 2026; originally announced January 2026.

Are These Even Words? Quantifying the Gibberishness of Generative Speech Models

Authors: Danilo de Oliveira, Tal Peer, Jonas Rochdi, Timo Gerkmann

Abstract: Significant research efforts are currently being dedicated to non-intrusive quality and intelligibility assessment, especially given how it enables curation of large scale datasets of in-the-wild speech data. However, with the increasing capabilities of generative models to synthesize high quality speech, new types of artifacts become relevant, such as generative hallucinations. While intrusive me… ▽ More Significant research efforts are currently being dedicated to non-intrusive quality and intelligibility assessment, especially given how it enables curation of large scale datasets of in-the-wild speech data. However, with the increasing capabilities of generative models to synthesize high quality speech, new types of artifacts become relevant, such as generative hallucinations. While intrusive metrics are able to spot such sort of discrepancies from a reference signal, it is not clear how current non-intrusive methods react to high-quality phoneme confusions or, more extremely, gibberish speech. In this paper we explore how to factor in this aspect under a fully unsupervised setting by leveraging language models. Additionally, we publish a dataset of high-quality synthesized gibberish speech for further development of measures to assess implausible sentences in spoken language, alongside code for calculating scores from a variety of speech language models. △ Less

Submitted 24 October, 2025; originally announced October 2025.

Toggling stiffness via multistability

Authors: Hugo de Souza Oliveira, Michele Curatolo, Renate Sachse, Edoardo Milana

Abstract: Variable stiffness is a key capability in biological and robotic systems, enabling adaptive interaction across tasks and environments. Mechanical metamaterials offer an alternative to conventional mechatronic solutions by encoding stiffness variation directly into monolithic structural architectures, reducing the need for discrete assemblies. Here, we introduce a multistable mechanical metamateria… ▽ More Variable stiffness is a key capability in biological and robotic systems, enabling adaptive interaction across tasks and environments. Mechanical metamaterials offer an alternative to conventional mechatronic solutions by encoding stiffness variation directly into monolithic structural architectures, reducing the need for discrete assemblies. Here, we introduce a multistable mechanical metamaterial that exhibits a toggleable stiffness effect in which the effective shear stiffness switches discretely between stable mechanical configurations. Mechanical analysis of surrogate beam models of the unit cell reveals that this behavior originates from the rotation transmitted by the support beams to the curved beam, governing the balance between bending and axial deformation. Consequently, the shear stiffness ratio between the two states can be tuned by varying the slenderness of the support beams or by incorporating localized hinges that modulate rotational transfer. Experiments on 3D-printed prototypes validate the numerical predictions and confirm consistent stiffness toggling across different geometries. Finally, we demonstrate a monolithic soft clutch that leverages this effect to achieve programmable, stepwise stiffness modulation. This work establishes a design strategy for toggleable stiffness using multistable metamaterials, with potential applications in soft robotics and smart structures where adaptive compliance is of paramount importance. △ Less

Submitted 5 May, 2026; v1 submitted 10 October, 2025; originally announced October 2025.

Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Models

Authors: Matheus Vinicius da Silva de Oliveira, Jonathan de Andrade Silva, Awdren de Lima Fontao

Abstract: Large Language Models (LLMs) are widely used across multiple domains but continue to raise concerns regarding security and fairness. Beyond known attack vectors such as data poisoning and prompt injection, LLMs are also vulnerable to fairness bugs. These refer to unintended behaviors influenced by sensitive demographic cues (e.g., race or sexual orientation) that should not affect outcomes. Anothe… ▽ More Large Language Models (LLMs) are widely used across multiple domains but continue to raise concerns regarding security and fairness. Beyond known attack vectors such as data poisoning and prompt injection, LLMs are also vulnerable to fairness bugs. These refer to unintended behaviors influenced by sensitive demographic cues (e.g., race or sexual orientation) that should not affect outcomes. Another key issue is hallucination, where models generate plausible yet false information. Retrieval-Augmented Generation (RAG) has emerged as a strategy to mitigate hallucinations by combining external retrieval with text generation. However, its adoption raises new fairness concerns, as the retrieved content itself may surface or amplify bias. This study conducts fairness testing through metamorphic testing (MT), introducing controlled demographic perturbations in prompts to assess fairness in sentiment analysis performed by three Small Language Models (SLMs) hosted on HuggingFace (Llama-3.2-3B-Instruct, Mistral-7B-Instruct-v0.3, and Llama-3.1-Nemotron-8B), each integrated into a RAG pipeline. Results show that minor demographic variations can break up to one third of metamorphic relations (MRs). A detailed analysis of these failures reveals a consistent bias hierarchy, with perturbations involving racial cues being the predominant cause of the violations. In addition to offering a comparative evaluation, this work reinforces that the retrieval component in RAG must be carefully curated to prevent bias amplification. The findings serve as a practical alert for developers, testers and small organizations aiming to adopt accessible SLMs without compromising fairness or reliability. △ Less

Submitted 30 September, 2025; originally announced September 2025.

Understanding Distribution Structure on Calibrated Recommendation Systems

Authors: Diego Correa da Silva, Denis Robson Dantas Boaventura, Mayki dos Santos Oliveira, Eduardo Ferreira da Silva, Joel Machado Pires, Frederico Araújo Durão

Abstract: Traditional recommender systems aim to generate a recommendation list comprising the most relevant or similar items to the user's profile. These approaches can create recommendation lists that omit item genres from the less prominent areas of a user's profile, thereby undermining the user's experience. To solve this problem, the calibrated recommendation system provides a guarantee of including le… ▽ More Traditional recommender systems aim to generate a recommendation list comprising the most relevant or similar items to the user's profile. These approaches can create recommendation lists that omit item genres from the less prominent areas of a user's profile, thereby undermining the user's experience. To solve this problem, the calibrated recommendation system provides a guarantee of including less representative areas in the recommended list. The calibrated context works with three distributions. The first is from the user's profile, the second is from the candidate items, and the last is from the recommendation list. These distributions are G-dimensional, where G is the total number of genres in the system. This high dimensionality requires a different evaluation method, considering that traditional recommenders operate in a one-dimensional data space. In this sense, we implement fifteen models that help to understand how these distributions are structured. We evaluate the users' patterns in three datasets from the movie domain. The results indicate that the models of outlier detection provide a better understanding of the structures. The calibrated system creates recommendation lists that act similarly to traditional recommendation lists, allowing users to change their groups of preferences to the same degree. △ Less

Submitted 19 August, 2025; originally announced August 2025.

ARCADE: A RAN Diagnosis Methodology in a Hybrid AI Environment for 6G Networks

Authors: Daniel Ricardo Cunha Oliveira, Rodrigo Moreira, Flávio de Oliveira Silva

Abstract: Artificial Intelligence (AI) plays a key role in developing 6G networks. While current specifications already include Network Data Analytics Function (NWDAF) as a network element responsible for providing information about the core, a more comprehensive approach will be needed to enable automation of network segments that are not yet fully explored in the context of 5G. In this paper, we present A… ▽ More Artificial Intelligence (AI) plays a key role in developing 6G networks. While current specifications already include Network Data Analytics Function (NWDAF) as a network element responsible for providing information about the core, a more comprehensive approach will be needed to enable automation of network segments that are not yet fully explored in the context of 5G. In this paper, we present Automated Radio Coverage Anomalies Detection and Evaluation (ARCADE), a methodology for identifying and diagnosing anomalies in the cellular access network. Furthermore, we demonstrate how a hybrid architecture of network analytics functions in the evolution toward 6G can enhance the application of AI in a broader network context, using ARCADE as a practical example of this approach. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Entity Re-identification in Visual Storytelling via Contrastive Reinforcement Learning

Authors: Daniel A. P. Oliveira, David Martins de Matos

Abstract: Visual storytelling systems, particularly large vision-language models, struggle to maintain character and object identity across frames, often failing to recognize when entities in different images represent the same individuals or objects, leading to inconsistent references and referential hallucinations. This occurs because models lack explicit training on when to establish entity connections a… ▽ More Visual storytelling systems, particularly large vision-language models, struggle to maintain character and object identity across frames, often failing to recognize when entities in different images represent the same individuals or objects, leading to inconsistent references and referential hallucinations. This occurs because models lack explicit training on when to establish entity connections across frames. We propose a contrastive reinforcement learning approach that trains models to discriminate between coherent image sequences and stories from unrelated images. We extend the Story Reasoning dataset with synthetic negative examples to teach appropriate entity connection behavior. We employ Direct Preference Optimization with a dual-component reward function that promotes grounding and re-identification of entities in real stories while penalizing incorrect entity connections in synthetic contexts. Using this contrastive framework, we fine-tune Qwen Storyteller (based on Qwen2.5-VL 7B). Evaluation shows improvements in grounding mAP from 0.27 to 0.31 (+14.8%), F1 from 0.35 to 0.41 (+17.1%). Pronoun grounding accuracy improved across all pronoun types except "its", and cross-frame character and object persistence increased across all frame counts, with entities appearing in 5 or more frames advancing from 29.3% to 33.3% (+13.7%). Well-structured stories, containing the chain-of-thought and grounded story, increased from 79.1% to 97.5% (+23.3%). △ Less

Submitted 10 July, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

Comments: 7 pages

ACM Class: I.2; I.4; I.5; I.7

3W Dataset 2.0.0: a realistic and public dataset with rare undesirable real events in oil wells

Authors: Ricardo Emanuel Vaz Vargas, Afrânio José de Melo Junior, Celso José Munaro, Cláudio Benevenuto de Campos Lima, Eduardo Toledo de Lima Junior, Felipe Muntzberg Barrocas, Flávio Miguel Varejão, Guilherme Fidelis Peixer, Igor de Melo Nery Oliveira, Jader Riso Barbosa Jr., Jaime Andrés Lozano Cadena, Jean Carlos Dias de Araújo, João Neuenschwander Escosteguy Carneiro, Lucas Gouveia Omena Lopes, Lucas Pereira de Gouveia, Mateus de Araujo Fernandes, Matheus Lima Scramignon, Patrick Marques Ciarelli, Rodrigo Castello Branco, Rogério Leite Alves Pinto

Abstract: In the oil industry, undesirable events in oil wells can cause economic losses, environmental accidents, and human casualties. Solutions based on Artificial Intelligence and Machine Learning for Early Detection of such events have proven valuable for diverse applications across industries. In 2019, recognizing the importance and the lack of public datasets related to undesirable events in oil well… ▽ More In the oil industry, undesirable events in oil wells can cause economic losses, environmental accidents, and human casualties. Solutions based on Artificial Intelligence and Machine Learning for Early Detection of such events have proven valuable for diverse applications across industries. In 2019, recognizing the importance and the lack of public datasets related to undesirable events in oil wells, Petrobras developed and publicly released the first version of the 3W Dataset, which is essentially a set of Multivariate Time Series labeled by experts. Since then, the 3W Dataset has been developed collaboratively and has become a foundational reference for numerous works in the field. This data article describes the current publicly available version of the 3W Dataset, which contains structural modifications and additional labeled data. The detailed description provided encourages and supports the 3W community and new 3W users to improve previous published results and to develop new robust methodologies, digital products and services capable of detecting undesirable events in oil wells with enough anticipation to enable corrective or mitigating actions. △ Less

Submitted 25 June, 2025; originally announced July 2025.

Comments: 21 pages, 10 figures, and 7 tables

LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models

Authors: Julius Richter, Danilo de Oliveira, Tal Peer, Timo Gerkmann

Abstract: We present LipDiffuser, a conditional diffusion model for lip-to-speech generation synthesizing natural and intelligible speech directly from silent video recordings. Our approach leverages the magnitude-preserving ablated diffusion model (MP-ADM) architecture as a denoiser model. To effectively condition the model, we incorporate visual features using magnitude-preserving feature-wise linear modu… ▽ More We present LipDiffuser, a conditional diffusion model for lip-to-speech generation synthesizing natural and intelligible speech directly from silent video recordings. Our approach leverages the magnitude-preserving ablated diffusion model (MP-ADM) architecture as a denoiser model. To effectively condition the model, we incorporate visual features using magnitude-preserving feature-wise linear modulation (MP-FiLM) alongside speaker embeddings. A neural vocoder then reconstructs the speech waveform from the generated mel-spectrograms. Evaluations on LRS3 demonstrate that LipDiffuser outperforms existing lip-to-speech baselines in perceptual speech quality and speaker similarity, while remaining competitive in downstream automatic speech recognition. These findings are also supported by a formal listening experiment. △ Less

Submitted 24 October, 2025; v1 submitted 16 May, 2025; originally announced May 2025.

StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation

Authors: Daniel A. P. Oliveira, David Martins de Matos

Abstract: Visual storytelling systems struggle to maintain character identity across frames and link actions to appropriate subjects, frequently leading to referential hallucinations. These issues can be addressed through grounding of characters, objects, and other entities on the visual elements. We propose StoryReasoning, a dataset containing 4,178 stories derived from 52,016 movie images, with both struc… ▽ More Visual storytelling systems struggle to maintain character identity across frames and link actions to appropriate subjects, frequently leading to referential hallucinations. These issues can be addressed through grounding of characters, objects, and other entities on the visual elements. We propose StoryReasoning, a dataset containing 4,178 stories derived from 52,016 movie images, with both structured scene analyses and grounded stories. Each story maintains character and object consistency across frames while explicitly modeling multi-frame relationships through structured tabular representations. Our approach features cross-frame object re-identification using visual similarity and face recognition, chain-of-thought reasoning for explicit narrative modeling, and a grounding scheme that links textual elements to visual entities across multiple frames. We establish baseline performance by fine-tuning Qwen2.5-VL 7B, creating Qwen Storyteller, which performs end-to-end object detection, re-identification, and landmark detection while maintaining consistent object references throughout the story. Evaluation demonstrates a reduction from 4.06 to 3.56 (-12.3%) hallucinations on average per story and an improvement in creativity from 2.58 to 3.38 (+31.0%) when compared to a non-fine-tuned model. △ Less

Submitted 30 August, 2025; v1 submitted 15 May, 2025; originally announced May 2025.

Comments: 31 pages, 14 figures

ACM Class: I.2.10; I.2.7

Do We Need EMA for Diffusion-Based Speech Enhancement? Toward a Magnitude-Preserving Network Architecture

Authors: Julius Richter, Danilo de Oliveira, Timo Gerkmann

Abstract: We study diffusion-based speech enhancement using a Schrodinger bridge formulation and extend the EDM2 framework to this setting. We employ time-dependent preconditioning of network inputs and outputs to stabilize training and explore two skip-connection configurations that allow the network to predict either environmental noise or clean speech. To control activation and weight magnitudes, we adop… ▽ More We study diffusion-based speech enhancement using a Schrodinger bridge formulation and extend the EDM2 framework to this setting. We employ time-dependent preconditioning of network inputs and outputs to stabilize training and explore two skip-connection configurations that allow the network to predict either environmental noise or clean speech. To control activation and weight magnitudes, we adopt a magnitude-preserving architecture and learn the contribution of the noisy input within each network block for improved conditioning. We further analyze the impact of exponential moving average (EMA) parameter smoothing by approximating different EMA profiles post training, finding that, unlike in image generation, short or absent EMA consistently yields better speech enhancement performance. Experiments on VoiceBank-DEMAND and EARS-WHAM demonstrate competitive signal-to-distortion ratios and perceptual scores, with the two skip-connection variants exhibiting complementary strengths. These findings provide new insights into EMA behavior, magnitude preservation, and skip-connection design for diffusion-based speech enhancement. △ Less

Submitted 29 January, 2026; v1 submitted 8 May, 2025; originally announced May 2025.

Comments: Accepted at ICASSP 2026

Performance of Large Language Models in Supporting Medical Diagnosis and Treatment

Authors: Diogo Sousa, Guilherme Barbosa, Catarina Rocha, Dulce Oliveira

Abstract: The integration of Large Language Models (LLMs) into healthcare holds significant potential to enhance diagnostic accuracy and support medical treatment planning. These AI-driven systems can analyze vast datasets, assisting clinicians in identifying diseases, recommending treatments, and predicting patient outcomes. This study evaluates the performance of a range of contemporary LLMs, including bo… ▽ More The integration of Large Language Models (LLMs) into healthcare holds significant potential to enhance diagnostic accuracy and support medical treatment planning. These AI-driven systems can analyze vast datasets, assisting clinicians in identifying diseases, recommending treatments, and predicting patient outcomes. This study evaluates the performance of a range of contemporary LLMs, including both open-source and closed-source models, on the 2024 Portuguese National Exam for medical specialty access (PNA), a standardized medical knowledge assessment. Our results highlight considerable variation in accuracy and cost-effectiveness, with several models demonstrating performance exceeding human benchmarks for medical students on this specific task. We identify leading models based on a combined score of accuracy and cost, discuss the implications of reasoning methodologies like Chain-of-Thought, and underscore the potential for LLMs to function as valuable complementary tools aiding medical professionals in complex clinical decision-making. △ Less

Submitted 14 April, 2025; originally announced April 2025.

Comments: 21 pages, 6 figures, 4 tables. Acknowledgements: The authors acknowledge the support of the AITriage4SU Project (2024.07400.IACDC/2024), funded by the FCT (Foundation for Science and Technology), Portugal

ACM Class: I.2.7; J.3

Proprioceptive multistable mechanical metamaterial via soft capacitive sensors

Authors: Hugo de Souza Oliveira, Niloofar Saeedzadeh Khaanghah, Martijn Oetelmans, Niko Münzenrieder, Edoardo Milana

Abstract: The technological transition from soft machines to soft robots necessarily passes through the integration of soft electronics and sensors. This allows for the establishment of feedback control systems while preserving the softness of the robot embodiment. Multistable mechanical metamaterials are excellent building blocks of soft machines, as their nonlinear response can be tuned by design to accom… ▽ More The technological transition from soft machines to soft robots necessarily passes through the integration of soft electronics and sensors. This allows for the establishment of feedback control systems while preserving the softness of the robot embodiment. Multistable mechanical metamaterials are excellent building blocks of soft machines, as their nonlinear response can be tuned by design to accomplish several functions. In this work, we present the integration of soft capacitive sensors in a multistable mechanical metamaterial, to enable proprioceptive sensing of state changes. The metamaterial is a periodic arrangement of 4 bistable unit cells. Each unit cell has an integrated capacitive sensor. Both the metastructure and the sensors are made of soft materials (TPU) and are 3D printed. Our preliminary results show that the capacitance variation of the sensors can be linked to state transitions of the metamaterial, by capturing the nonlinear deformation. △ Less

Submitted 30 March, 2025; originally announced March 2025.

Comments: 2024 IEEE International Flexible Electronics Technology Conference (IFETC)

Meta-Ori: monolithic meta-origami for nonlinear inflatable soft actuators

Authors: Hugo de Souza Oliveira, Xin Li, Johannes Frey, Edoardo Milana

Abstract: The nonlinear mechanical response of soft materials and slender structures is purposefully harnessed to program functions by design in soft robotic actuators, such as sequencing, amplified response, fast energy release, etc. However, typical designs of nonlinear actuators - e.g. balloons, inverted membranes, springs - have limited design parameters space and complex fabrication processes, hinderin… ▽ More The nonlinear mechanical response of soft materials and slender structures is purposefully harnessed to program functions by design in soft robotic actuators, such as sequencing, amplified response, fast energy release, etc. However, typical designs of nonlinear actuators - e.g. balloons, inverted membranes, springs - have limited design parameters space and complex fabrication processes, hindering the achievement of more elaborated functions. Mechanical metamaterials, on the other hand, have very large design parameter spaces, which allow fine-tuning of nonlinear behaviours. In this work, we present a novel approach to fabricate nonlinear inflatables based on metamaterials and origami (Meta-Ori) as monolithic parts that can be fully 3D printed via Fused Deposition Modeling (FDM) using thermoplastic polyurethane (TPU) commercial filaments. Our design consists of a metamaterial shell with cylindrical topology and nonlinear mechanical response combined with a Kresling origami inflatable acting as a pneumatic transmitter. We develop and release a design tool in the visual programming language Grasshopper to interactively design our Meta-Ori. We characterize the mechanical response of the metashell and the origami, and the nonlinear pressure-volume curve of the Meta-Ori inflatable and, lastly, we demonstrate the actuation sequencing of a bi-segment monolithic Meta-Ori soft actuator. △ Less

Submitted 30 March, 2025; originally announced March 2025.

Comments: 8th IEEE-RAS International Conference on Soft Robotics

CountPath: Automating Fragment Counting in Digital Pathology

Authors: Ana Beatriz Vieira, Maria Valente, Diana Montezuma, Tomé Albuquerque, Liliana Ribeiro, Domingos Oliveira, João Monteiro, Sofia Gonçalves, Isabel M. Pinto, Jaime S. Cardoso, Arlindo L. Oliveira

Abstract: Quality control of medical images is a critical component of digital pathology, ensuring that diagnostic images meet required standards. A pre-analytical task within this process is the verification of the number of specimen fragments, a process that ensures that the number of fragments on a slide matches the number documented in the macroscopic report. This step is important to ensure that the sl… ▽ More Quality control of medical images is a critical component of digital pathology, ensuring that diagnostic images meet required standards. A pre-analytical task within this process is the verification of the number of specimen fragments, a process that ensures that the number of fragments on a slide matches the number documented in the macroscopic report. This step is important to ensure that the slides contain the appropriate diagnostic material from the grossing process, thereby guaranteeing the accuracy of subsequent microscopic examination and diagnosis. Traditionally, this assessment is performed manually, requiring significant time and effort while being subject to significant variability due to its subjective nature. To address these challenges, this study explores an automated approach to fragment counting using the YOLOv9 and Vision Transformer models. Our results demonstrate that the automated system achieves a level of performance comparable to expert assessments, offering a reliable and efficient alternative to manual counting. Additionally, we present findings on interobserver variability, showing that the automated approach achieves an accuracy of 86%, which falls within the range of variation observed among experts (82-88%), further supporting its potential for integration into routine pathology workflows. △ Less

Submitted 13 March, 2025; originally announced March 2025.

Comments: 10 pages, 3 figures

ACM Class: I.2; I.4

i-WiViG: Interpretable Window Vision GNN

Authors: Ivica Obadic, Dmitry Kangin, Adrian Höhl, Dario Oliveira, Plamen P Angelov, Xiao Xiang Zhu

Abstract: Vision graph neural networks have emerged as a popular approach for modeling the global and spatial context for image recognition. However, a significant drawback of these methods is that they do not offer an inherent interpretation of the relevant spatial interactions for their prediction. We address this problem by introducing i-WiViG, an approach that enables interpretable model reasoning based… ▽ More Vision graph neural networks have emerged as a popular approach for modeling the global and spatial context for image recognition. However, a significant drawback of these methods is that they do not offer an inherent interpretation of the relevant spatial interactions for their prediction. We address this problem by introducing i-WiViG, an approach that enables interpretable model reasoning based on a sparse subgraph in the image. i-WiViG is based on two key postulates: 1) constraining the graph nodes' receptive field to disjoint local windows in the image, and 2) an inherently interpretable graph bottleneck with learnable sparse attention that identifies the relevant interactions among the local image windows. We evaluate our approach on both scene classification and regression tasks using natural and remote sensing imagery. Our results, supported by quantitative and qualitative evidence, demonstrate that the method delivers semantic, intuitive, and faithful explanations through the identified subgraphs. Furthermore, extensive experiments confirm that it achieves competitive performance to its black-box counterparts, even on datasets exhibiting strong texture bias. The implementation is available on https://github.com/zhu-xlab/i-WiViG. △ Less

Submitted 21 April, 2026; v1 submitted 11 March, 2025; originally announced March 2025.

REGRACE: A Robust and Efficient Graph-based Re-localization Algorithm using Consistency Evaluation

Authors: Débora N. P. Oliveira, Joshua Knights, Sebastián Barbas Laina, Simon Boche, Wolfram Burgard, Stefan Leutenegger

Abstract: Loop closures are essential for correcting odometry drift and creating consistent maps, especially in the context of large-scale navigation. Current methods using dense point clouds for accurate place recognition do not scale well due to computationally expensive scan-to-scan comparisons. Alternative object-centric approaches are more efficient but often struggle with sensitivity to viewpoint vari… ▽ More Loop closures are essential for correcting odometry drift and creating consistent maps, especially in the context of large-scale navigation. Current methods using dense point clouds for accurate place recognition do not scale well due to computationally expensive scan-to-scan comparisons. Alternative object-centric approaches are more efficient but often struggle with sensitivity to viewpoint variation. In this work, we introduce REGRACE, a novel approach that addresses these challenges of scalability and perspective difference in re-localization by using LiDAR-based submaps. We introduce rotation-invariant features for each labeled object and enhance them with neighborhood context through a graph neural network. To identify potential revisits, we employ a scalable bag-of-words approach, pooling one learned global feature per submap. Additionally, we define a revisit with geometrical consistency cues rather than embedding distance, allowing us to recognize far-away loop closures. Our evaluations demonstrate that REGRACE achieves similar results compared to state-of-the-art place recognition and registration baselines while being twice as fast. Code and models are publicly available. △ Less

Submitted 28 July, 2025; v1 submitted 5 March, 2025; originally announced March 2025.

Comments: Accepted to IROS2025

GroundCap: A Visually Grounded Image Captioning Dataset

Authors: Daniel A. P. Oliveira, Lourenço Teodoro, David Martins de Matos

Abstract: Current image captioning systems lack the ability to link descriptive text to specific visual elements, making their outputs difficult to verify. While recent approaches offer some grounding capabilities, they cannot track object identities across multiple references or ground both actions and objects simultaneously. We propose a novel ID-based grounding system that enables consistent object refer… ▽ More Current image captioning systems lack the ability to link descriptive text to specific visual elements, making their outputs difficult to verify. While recent approaches offer some grounding capabilities, they cannot track object identities across multiple references or ground both actions and objects simultaneously. We propose a novel ID-based grounding system that enables consistent object reference tracking and action-object linking. We present GroundCap, a dataset containing 52,016 images from 77 movies, with 344 human-annotated and 52,016 automatically generated captions. Each caption is grounded on detected objects (132 classes) and actions (51 classes) using a tag system that maintains object identity while linking actions to the corresponding objects. Our approach features persistent object IDs for reference tracking, explicit action-object linking, and the segmentation of background elements through K-means clustering. We propose gMETEOR, a metric combining caption quality with grounding accuracy, and establish baseline performance by fine-tuning Pixtral-12B and Qwen2.5-VL 7B on GroundCap. Human evaluation demonstrates our approach's effectiveness in producing verifiable descriptions with coherent object references. △ Less

Submitted 25 June, 2025; v1 submitted 19 February, 2025; originally announced February 2025.

Comments: 37 pages

ACM Class: I.2.10; I.2.7

Mamute: high-performance computing for geophysical methods

Authors: João B. Fernandes, Antônio D. S. Oliveira, Mateus C. A. T. Silva, Felipe H. Santos-da-Silva, Vitor H. M. Rodrigues, Kleiton A. Schneider, Calebe P. Bianchini, João M. de Araujo, Tiago Barros, Ítalo A. S. Assis, Samuel Xavier-de-Souza

Abstract: Due to their high computational cost, geophysical applications are typically designed to run in large computing systems. Because of that, such applications must implement several high-performance techniques to use the computational resources better. In this paper, we present Mamute, a software that delivers wave equation-based geophysical methods. Mamute implements two geophysical methods: seismic… ▽ More Due to their high computational cost, geophysical applications are typically designed to run in large computing systems. Because of that, such applications must implement several high-performance techniques to use the computational resources better. In this paper, we present Mamute, a software that delivers wave equation-based geophysical methods. Mamute implements two geophysical methods: seismic modeling and full waveform inversion (FWI). It also supports high-performance strategies such as fault tolerance, automatic parallel looping scheduling, and distributed systems workload balancing. We demonstrate Mamute's operation using both seismic modeling and FWI. Mamute is a C++ software readily available under the MIT license. △ Less

Submitted 17 February, 2025; originally announced February 2025.

Comments: 24 pages, 6 figures, Journal

Navigating Gender Disparities in Communication Research Leadership: Academic Recognition, Career Development, and Compensation

Authors: Diego F. M. Oliveira, Qian Huang

Abstract: This study examines gender disparities in communication research through citation metrics, authorship patterns, team composition, and faculty salaries. Using data from 62,359 papers across 121 communication journals, we find that while female authors are increasingly represented, citation gaps persist, with sole-authored papers by women receiving fewer citations than those by men, especially in sm… ▽ More This study examines gender disparities in communication research through citation metrics, authorship patterns, team composition, and faculty salaries. Using data from 62,359 papers across 121 communication journals, we find that while female authors are increasingly represented, citation gaps persist, with sole-authored papers by women receiving fewer citations than those by men, especially in smaller teams. Team composition analysis reveals a tendency toward gender homophily, with single-gender teams being more common. In top U.S. communication journals, female authors face underrepresentation and citation disparities favoring male authors. Salary analysis from leading U.S. public universities shows that female faculty earn lower salaries at the Assistant Professor level, though disparities lessen at higher ranks. These findings highlight the need for greater efforts to promote gender equity through inclusive collaboration, equitable citation practices, and fair compensation. △ Less

Submitted 15 January, 2025; v1 submitted 14 January, 2025; originally announced January 2025.

Finding the Underlying Viscoelastic Constitutive Equation via Universal Differential Equations and Differentiable Physics

Authors: Elias C. Rodrigues, Roney L. Thompson, Dário A. B. Oliveira, Roberto F. Ausas

Abstract: This research employs Universal Differential Equations (UDEs) alongside differentiable physics to model viscoelastic fluids, merging conventional differential equations, neural networks and numerical methods to reconstruct missing terms in constitutive models. This study focuses on analyzing four viscoelastic models: Upper Convected Maxwell (UCM), Johnson-Segalman, Giesekus, and Exponential Phan-T… ▽ More This research employs Universal Differential Equations (UDEs) alongside differentiable physics to model viscoelastic fluids, merging conventional differential equations, neural networks and numerical methods to reconstruct missing terms in constitutive models. This study focuses on analyzing four viscoelastic models: Upper Convected Maxwell (UCM), Johnson-Segalman, Giesekus, and Exponential Phan-Thien-Tanner (ePTT), through the use of synthetic datasets. The methodology was tested across different experimental conditions, including oscillatory and startup flows. While the UDE framework effectively predicts shear and normal stresses for most models, it demonstrates some limitations when applied to the ePTT model. The findings underscore the potential of UDEs in fluid mechanics while identifying critical areas for methodological improvement. Also, a model distillation approach was employed to extract simplified models from complex ones, emphasizing the versatility and robustness of UDEs in rheological modeling. △ Less

Submitted 23 May, 2025; v1 submitted 31 December, 2024; originally announced January 2025.

Seq2Seq Model-Based Chatbot with LSTM and Attention Mechanism for Enhanced User Interaction

Authors: Lamya Benaddi, Charaf Ouaddi, Adnane Souha, Abdeslam Jakimi, Mohamed Rahouti, Mohammed Aledhari, Diogo Oliveira, Brahim Ouchao

Abstract: A chatbot is an intelligent software application that automates conversations and engages users in natural language through messaging platforms. Leveraging artificial intelligence (AI), chatbots serve various functions, including customer service, information gathering, and casual conversation. Existing virtual assistant chatbots, such as ChatGPT and Gemini, demonstrate the potential of AI in Natu… ▽ More A chatbot is an intelligent software application that automates conversations and engages users in natural language through messaging platforms. Leveraging artificial intelligence (AI), chatbots serve various functions, including customer service, information gathering, and casual conversation. Existing virtual assistant chatbots, such as ChatGPT and Gemini, demonstrate the potential of AI in Natural Language Processing (NLP). However, many current solutions rely on predefined APIs, which can result in vendor lock-in and high costs. To address these challenges, this work proposes a chatbot developed using a Sequence-to-Sequence (Seq2Seq) model with an encoder-decoder architecture that incorporates attention mechanisms and Long Short-Term Memory (LSTM) cells. By avoiding predefined APIs, this approach ensures flexibility and cost-effectiveness. The chatbot is trained, validated, and tested on a dataset specifically curated for the tourism sector in Draa-Tafilalet, Morocco. Key evaluation findings indicate that the proposed Seq2Seq model-based chatbot achieved high accuracies: approximately 99.58% in training, 98.03% in validation, and 94.12% in testing. These results demonstrate the chatbot's effectiveness in providing relevant and coherent responses within the tourism domain, highlighting the potential of specialized AI applications to enhance user experience and satisfaction in niche markets. △ Less

Submitted 27 December, 2024; originally announced January 2025.

Comments: The Third Workshop on Deployable AI at AAAI-2025

FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigation

Authors: Samiran Gode, Abhijeet Nayak, Débora N. P. Oliveira, Michael Krawez, Cordelia Schmid, Wolfram Burgard

Abstract: Effective robot navigation in unseen environments is a challenging task that requires precise control actions at high frequencies. Recent advances have framed it as an image-goal-conditioned control problem, where the robot generates navigation actions using frontal RGB images. Current state-of-the-art methods in this area use diffusion policies to generate these control actions. Despite their pro… ▽ More Effective robot navigation in unseen environments is a challenging task that requires precise control actions at high frequencies. Recent advances have framed it as an image-goal-conditioned control problem, where the robot generates navigation actions using frontal RGB images. Current state-of-the-art methods in this area use diffusion policies to generate these control actions. Despite their promising results, these models are computationally expensive and suffer from weak perception. To address these limitations, we present FlowNav, a novel approach that uses a combination of CFM and depth priors from off-the-shelf foundation models to learn action policies for robot navigation. FlowNav is significantly more accurate and faster at navigation and exploration than state-of-the-art methods. We validate our contributions using real robot experiments in multiple environments, demonstrating improved navigation reliability and accuracy. Code and trained models are publicly available. △ Less

Submitted 28 July, 2025; v1 submitted 14 November, 2024; originally announced November 2024.

Comments: Accepted to IROS'25. Previous version accepted at CoRL 2024 workshop on Learning Effective Abstractions for Planning (LEAP) and workshop on Differentiable Optimization Everywhere: Simulation, Estimation, Learning, and Control

Understanding Code Understandability Improvements in Code Reviews

Authors: Delano Oliveira, Reydne Santos, Benedito de Oliveira, Martin Monperrus, Fernando Castor, Fernanda Madeiral

Abstract: Motivation: Code understandability is crucial in software development, as developers spend 58% to 70% of their time reading source code. Improving it can improve productivity and reduce maintenance costs. Problem: Experimental studies often identify factors influencing code understandability in controlled settings but overlook real-world influences like project culture, guidelines, and developers'… ▽ More Motivation: Code understandability is crucial in software development, as developers spend 58% to 70% of their time reading source code. Improving it can improve productivity and reduce maintenance costs. Problem: Experimental studies often identify factors influencing code understandability in controlled settings but overlook real-world influences like project culture, guidelines, and developers' backgrounds. Ignoring these factors may yield results with limited external validity. Objective: This study investigates how developers enhance code understandability through code review comments, assuming that code reviewers are specialists in code quality. Method and Results: We analyzed 2,401 code review comments from Java open-source projects on GitHub, finding that over 42% focus on improving code understandability. We further examined 385 comments specifically related to this aspect and identified eight categories of concerns, such as inadequate documentation and poor identifiers. Notably, 83.9% of suggestions for improvement were accepted and integrated, with fewer than 1% later reverted. We identified various types of patches that enhance understandability, from simple changes like removing unused code to context-dependent improvements such as optimizing method calls. Additionally, we evaluated four well-known linters for their ability to flag these issues, finding they cover less than 30%, although many could be easily added as new rules. Implications: Our findings encourage the development of tools to enhance code understandability, as accepted changes can serve as reliable training data for specialized machine-learning models. Our dataset supports this training and can inform the development of evidence-based code style guides. Data Availability: Our data is publicly available at https://codeupcrc.github.io. △ Less

Submitted 12 November, 2024; v1 submitted 29 October, 2024; originally announced October 2024.

Journal ref: IEEE Transactions on Software Engineering, 2024

Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech

Authors: Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann

Abstract: Diffusion models have found great success in generating high quality, natural samples of speech, but their potential for density estimation for speech has so far remained largely unexplored. In this work, we leverage an unconditional diffusion model trained only on clean speech for the assessment of speech quality. We show that the quality of a speech utterance can be assessed by estimating the li… ▽ More Diffusion models have found great success in generating high quality, natural samples of speech, but their potential for density estimation for speech has so far remained largely unexplored. In this work, we leverage an unconditional diffusion model trained only on clean speech for the assessment of speech quality. We show that the quality of a speech utterance can be assessed by estimating the likelihood of a corresponding sample in the terminating Gaussian distribution, obtained via a deterministic noising process. The resulting method is purely unsupervised, trained only on clean speech, and therefore does not rely on annotations. Our diffusion-based approach leverages clean speech priors to assess quality based on how the input relates to the learned distribution of clean data. Our proposed log-likelihoods show promising results, correlating well with intrusive speech quality metrics and showing the best correlation with human scores in a listening experiment. △ Less

Submitted 13 June, 2025; v1 submitted 23 October, 2024; originally announced October 2024.

Comments: Accepted at Interspeech 2025

Workflows Community Summit 2024: Future Trends and Challenges in Scientific Workflows

Authors: Rafael Ferreira da Silva, Deborah Bard, Kyle Chard, Shaun de Witt, Ian T. Foster, Tom Gibbs, Carole Goble, William Godoy, Johan Gustafsson, Utz-Uwe Haus, Stephen Hudson, Shantenu Jha, Laila Los, Drew Paine, Frédéric Suter, Logan Ward, Sean Wilkinson, Marcos Amaris, Yadu Babuji, Jonathan Bader, Riccardo Balin, Daniel Balouek, Sarah Beecroft, Khalid Belhajjame, Rajat Bhattarai , et al. (86 additional authors not shown)

Abstract: The Workflows Community Summit gathered 111 participants from 18 countries to discuss emerging trends and challenges in scientific workflows, focusing on six key areas: time-sensitive workflows, AI-HPC convergence, multi-facility workflows, heterogeneous HPC environments, user experience, and FAIR computational workflows. The integration of AI and exascale computing has revolutionized scientific w… ▽ More The Workflows Community Summit gathered 111 participants from 18 countries to discuss emerging trends and challenges in scientific workflows, focusing on six key areas: time-sensitive workflows, AI-HPC convergence, multi-facility workflows, heterogeneous HPC environments, user experience, and FAIR computational workflows. The integration of AI and exascale computing has revolutionized scientific workflows, enabling higher-fidelity models and complex, time-sensitive processes, while introducing challenges in managing heterogeneous environments and multi-facility data dependencies. The rise of large language models is driving computational demands to zettaflop scales, necessitating modular, adaptable systems and cloud-service models to optimize resource utilization and ensure reproducibility. Multi-facility workflows present challenges in data movement, curation, and overcoming institutional silos, while diverse hardware architectures require integrating workflow considerations into early system design and developing standardized resource management tools. The summit emphasized improving user experience in workflow systems and ensuring FAIR workflows to enhance collaboration and accelerate scientific discovery. Key recommendations include developing standardized metrics for time-sensitive workflows, creating frameworks for cloud-HPC integration, implementing distributed-by-design workflow modeling, establishing multi-facility authentication protocols, and accelerating AI integration in HPC workflow management. The summit also called for comprehensive workflow benchmarks, workflow-specific UX principles, and a FAIR workflow maturity model, highlighting the need for continued collaboration in addressing the complex challenges posed by the convergence of AI, HPC, and multi-facility research environments. △ Less

Submitted 18 October, 2024; originally announced October 2024.

Report number: ORNL/TM-2024/3573

Urban Computing for Climate and Environmental Justice: Early Perspectives From Two Research Initiatives

Authors: Carolina Veiga, Ashish Sharma, Daniel de Oliveira, Marcos Lage, Fabio Miranda

Abstract: The impacts of climate change are intensifying existing vulnerabilities and disparities within urban communities around the globe, as extreme weather events, including floods and heatwaves, are becoming more frequent and severe, disproportionately affecting low-income and underrepresented groups. Tackling these increasing challenges requires novel approaches that integrate expertise across multipl… ▽ More The impacts of climate change are intensifying existing vulnerabilities and disparities within urban communities around the globe, as extreme weather events, including floods and heatwaves, are becoming more frequent and severe, disproportionately affecting low-income and underrepresented groups. Tackling these increasing challenges requires novel approaches that integrate expertise across multiple domains, including computer science, engineering, climate science, and public health. Urban computing can play a pivotal role in these efforts by integrating data from multiple sources to support decision-making and provide actionable insights into weather patterns, infrastructure weaknesses, and population vulnerabilities. However, the capacity to leverage technological advancements varies significantly between the Global South and Global North. In this paper, we present two multiyear, multidisciplinary projects situated in Chicago, USA and Niterói, Brazil, highlighting the opportunities and limitations of urban computing in these diverse contexts. Reflecting on our experiences, we then discuss the essential requirements, as well as existing gaps, for visual analytics tools that facilitate the understanding and mitigation of climate-related risks in urban environments. △ Less

Submitted 5 October, 2024; originally announced October 2024.

Comments: Accepted at the Viz4Climate + Sustainability: IEEE VIS 2024 Workshop on Visualization for Climate Action and Sustainability (https://svs.gsfc.nasa.gov/events/2024/Viz4ClimateAndSustainability/)

Investigating Training Objectives for Generative Speech Enhancement

Authors: Julius Richter, Danilo de Oliveira, Timo Gerkmann

Abstract: Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This paper aims to explain the differences between these frameworks by focusing our investigation on score-based generative models and the Schrödinger bridge. We con… ▽ More Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This paper aims to explain the differences between these frameworks by focusing our investigation on score-based generative models and the Schrödinger bridge. We conduct a series of comprehensive experiments to compare their performance and highlight differing training behaviors. Furthermore, we propose a novel perceptual loss function tailored for the Schrödinger bridge framework, demonstrating enhanced performance and improved perceptual quality of the enhanced speech signals. All experimental code and pre-trained models are publicly available to facilitate further research and development in this domain. △ Less

Submitted 18 January, 2025; v1 submitted 16 September, 2024; originally announced September 2024.

Comments: Accepted at ICASSP 2025

Computer Vision Model Compression Techniques for Embedded Systems: A Survey

Authors: Alexandre Lopes, Fernando Pereira dos Santos, Diulhio de Oliveira, Mauricio Schiezaro, Helio Pedrini

Abstract: Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with plenty of representative data. With the recent adoption of Vision Transformer (ViT) based architectures and advanced Convolutional Neural Networks (C… ▽ More Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with plenty of representative data. With the recent adoption of Vision Transformer (ViT) based architectures and advanced Convolutional Neural Networks (CNNs), the total number of parameters of leading backbone architectures increased from 62M parameters in 2012 with AlexNet to 7B parameters in 2024 with AIM-7B. Consequently, deploying such deep architectures faces challenges in environments with processing and runtime constraints, particularly in embedded systems. This paper covers the main model compression techniques applied for computer vision tasks, enabling modern models to be used in embedded systems. We present the characteristics of compression subareas, compare different approaches, and discuss how to choose the best technique and expected variations when analyzing it on various embedded devices. We also share codes to assist researchers and new practitioners in overcoming initial implementation challenges for each subarea and present trends for Model Compression. Case studies for compression models are available at \href{https://github.com/venturusbr/cv-model-compression}{https://github.com/venturusbr/cv-model-compression}. △ Less

Submitted 15 August, 2024; originally announced August 2024.

Journal ref: Computers & Graphics, Volume 123, October 2024, 104015

MyoGestic: EMG Interfacing Framework for Decoding Multiple Spared Degrees of Freedom of the Hand in Individuals with Neural Lesions

Authors: Raul C. Sîmpetru, Dominik I. Braun, Arndt U. Simon, Michael März, Vlad Cnejevici, Daniela Souza de Oliveira, Nico Weber, Jonas Walter, Jörg Franke, Daniel Höglinger, Cosima Prahm, Matthias Ponfick, Alessandro Del Vecchio

Abstract: Restoring limb motor function in individuals with spinal cord injury (SCI), stroke, or amputation remains a critical challenge, one which affects millions worldwide. Recent studies show through surface electromyography (EMG) that spared motor neurons can still be voluntarily controlled, even without visible limb movement . These signals can be decoded and used for motor intent estimation; however,… ▽ More Restoring limb motor function in individuals with spinal cord injury (SCI), stroke, or amputation remains a critical challenge, one which affects millions worldwide. Recent studies show through surface electromyography (EMG) that spared motor neurons can still be voluntarily controlled, even without visible limb movement . These signals can be decoded and used for motor intent estimation; however, current wearable solutions lack the necessary hardware and software for intuitive interfacing of the spared degrees of freedom after neural injuries. To address these limitations, we developed a wireless, high-density EMG bracelet, coupled with a novel software framework, MyoGestic. Our system allows rapid and tailored adaptability of machine learning models to the needs of the users, facilitating real-time decoding of multiple spared distinctive degrees of freedom. In our study, we successfully decoded the motor intent from two participants with SCI, two with spinal stroke , and three amputees in real-time, achieving several controllable degrees of freedom within minutes after wearing the EMG bracelet. We provide a proof-of-concept that these decoded signals can be used to control a digitally rendered hand, a wearable orthosis, a prosthesis, or a 2D cursor. Our framework promotes a participant-centered approach, allowing immediate feedback integration, thus enhancing the iterative development of myocontrol algorithms. The proposed open-source software framework, MyoGestic, allows researchers and patients to focus on the augmentation and training of the spared degrees of freedom after neural lesions, thus potentially bridging the gap between research and clinical application and advancing the development of intuitive EMG interfaces for diverse neural lesions. △ Less

Submitted 14 August, 2024; originally announced August 2024.

Comments: 23 pages, 8 figures

ACM Class: H.5.2; J.3; I.5.4; D.2.13

Journal ref: Science Advances, 11, 2025, eads9150

Curio: A Dataflow-Based Framework for Collaborative Urban Visual Analytics

Authors: Gustavo Moreira, Maryam Hosseini, Carolina Veiga, Lucas Alexandre, Nicola Colaninno, Daniel de Oliveira, Nivan Ferreira, Marcos Lage, Fabio Miranda

Abstract: Over the past decade, several urban visual analytics systems and tools have been proposed to tackle a host of challenges faced by cities, in areas as diverse as transportation, weather, and real estate. Many of these tools have been designed through collaborations with urban experts, aiming to distill intricate urban analysis workflows into interactive visualizations and interfaces. However, the d… ▽ More Over the past decade, several urban visual analytics systems and tools have been proposed to tackle a host of challenges faced by cities, in areas as diverse as transportation, weather, and real estate. Many of these tools have been designed through collaborations with urban experts, aiming to distill intricate urban analysis workflows into interactive visualizations and interfaces. However, the design, implementation, and practical use of these tools still rely on siloed approaches, resulting in bespoke applications that are difficult to reproduce and extend. At the design level, these tools undervalue rich data workflows from urban experts, typically treating them only as data providers and evaluators. At the implementation level, they lack interoperability with other technical frameworks. At the practical use level, they tend to be narrowly focused on specific fields, inadvertently creating barriers to cross-domain collaboration. To address these gaps, we present Curio, a framework for collaborative urban visual analytics. Curio uses a dataflow model with multiple abstraction levels (code, grammar, GUI elements) to facilitate collaboration across the design and implementation of visual analytics components. The framework allows experts to intertwine data preprocessing, management, and visualization stages while tracking the provenance of code and visualizations. In collaboration with urban experts, we evaluate Curio through a diverse set of usage scenarios targeting urban accessibility, urban microclimate, and sunlight access. These scenarios use different types of data and domain methodologies to illustrate Curio's flexibility in tackling pressing societal challenges. Curio is available at https://urbantk.org/curio. △ Less

Submitted 12 August, 2024; originally announced August 2024.

Comments: Accepted at IEEE VIS 2024. Source code available at https://urbantk.org/curio