Showing 1–50 of 206 results for author: Da, C

GADR: Gathering Architecture Decision Records from Meeting Transcriptions

Authors: Lucas Daniel Costa da Silva, Kiev Gama

Abstract: Existing LLM-based approaches to Architecture Decision Record (ADR) generation share a critical and largely unexamined assumption: that input is already reasonably structured. In practice, architectural decisions emerge from informal, noisy meetings where choices are implicit, fragmented, and entangled with off-topic dialogue, precisely the conditions under which single-pass prompting degrades. Th… ▽ More Existing LLM-based approaches to Architecture Decision Record (ADR) generation share a critical and largely unexamined assumption: that input is already reasonably structured. In practice, architectural decisions emerge from informal, noisy meetings where choices are implicit, fragmented, and entangled with off-topic dialogue, precisely the conditions under which single-pass prompting degrades. This paper presents GADR, a multi-agent, self-correcting workflow that extracts architectural decisions from raw meeting transcriptions and generates Nygard-formatted ADR drafts. A feasibility study comprising five real project meeting transcripts, expert review by four senior architects, and evaluation by fifteen students provides initial evidence that the agentic workflow captures most expert-identified decisions and produces drafts participants found clear and useful, outperforming zero-shot and few-shot baselines in stability and structural adherence. The study also addresses the underexplored trade-off of RAG-based enrichment improving ADR depth while simultaneously risking transcript-unfaithful content, raising open questions about traceability in automated architectural documentation that we believe is worth the community's attention. △ Less

Submitted 18 August, 2026; originally announced August 2026.

The Brazilian Vaccination Debate on YouTube: Topics, Perspectives, and Engagement Dynamics

Authors: Matheus S. Azevedo, Geovana S. de Oliveira, Andrea Failla, Alexandre M. de Sousa, Fabricio Murai, Ana Paula C. da Silva, Carlos H. G. Ferreira

Abstract: Vaccination debates are central to online public health communication, as COVID-19 intensified disputes over scientific authority, institutional trust, and political identity. Yet studies often isolate semantic structure, stance, misinformation, and engagement, leaving their interplay over time poorly understood. We conduct a multilevel computational text analysis based on language models applied… ▽ More Vaccination debates are central to online public health communication, as COVID-19 intensified disputes over scientific authority, institutional trust, and political identity. Yet studies often isolate semantic structure, stance, misinformation, and engagement, leaving their interplay over time poorly understood. We conduct a multilevel computational text analysis based on language models applied to 1.27 million Brazilian YouTube comments from 2018 to 2024, using what is, to our knowledge, the largest dataset of Brazilian vaccine discourse on the Web. We contrast producer framing in titles with audience discourse in comments, integrating Topic-derived themes with engagement metadata, conversational timing, stance-derived vaccine positions, and pre-pandemic, pandemic, and post-pandemic periods. Results show that COVID-19 dominates biomedical and informational themes in titles, whereas comments span personal health reports, vaccine effects, information credibility, conspiracy narratives, and political disputes. Health-related macro-topics dominate in scale and persistence, while conspiratorial and political themes are associated with faster interactions and a greater concentration of vaccine-opposing engagement. Post-pandemic activity remains centered on health experiences, vaccine effects, and information credibility, indicating no return to the pre-pandemic thematic configuration. By integrating semantic, interactional, stance, and temporal dimensions, this study shows how audiences reframe producer-framed health content and how vaccine controversies persist beyond the acute pandemic period. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Comments: Accepted at ASONAM 2026

Greedy approaches for Gold Grabbing on subclasses of split graphs

Authors: Heitor Melo de Lucas Brandão, Hebert Coelho da Silva, Julliano Rosa Nascimento

Abstract: The Gold Grabbing Game is a combinatorial game on vertex-weighted graphs in which two players alternately remove vertices while maintaining graph connectivity, aiming to maximize the total collected weight. Although the literature has primarily focused on strategies that guarantee victory, the question of optimality --- i.e., maximizing total gain --- remains less explored. In this work, we invest… ▽ More The Gold Grabbing Game is a combinatorial game on vertex-weighted graphs in which two players alternately remove vertices while maintaining graph connectivity, aiming to maximize the total collected weight. Although the literature has primarily focused on strategies that guarantee victory, the question of optimality --- i.e., maximizing total gain --- remains less explored. In this work, we investigate the behavior of the greedy strategy in this setting. We show that this approach is not optimal for general split graphs, highlighting structural limitations of this class. On the other hand, we prove that for complete split graphs $CS_{(2,n)}$, the greedy strategy yields a sequence of moves that maximizes the game value. As a consequence, the first player does not lose when the number of vertices is even. These results contribute to a better understanding of the structural conditions that ensure the optimality of simple strategies in graph-based combinatorial games. △ Less

Submitted 12 August, 2026; originally announced August 2026.

SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization

Authors: Nguyen Viet Tuan Kiet, Nguyen Huu Duc, Le Cong Bang, Tran Cong Dao, Huynh Thi Thanh Binh

Abstract: Black-box combinatorial optimization requires systematically identifying high-quality solutions under a limited evaluation budget, yet the unknown objective function provides little guidance for deciding where the search should explore next. We introduce SCOPE, a general framework for Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization. Rather than directl… ▽ More Black-box combinatorial optimization requires systematically identifying high-quality solutions under a limited evaluation budget, yet the unknown objective function provides little guidance for deciding where the search should explore next. We introduce SCOPE, a general framework for Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization. Rather than directly optimizing the inaccessible objective, SCOPE learns a set of synthetic objectives conditioned on the accumulated search history, where each objective is designed to expose a distinct and potentially useful preference over candidate solutions. These objectives are then used to evolve search policies that generate diverse candidates, whose true quality is subsequently assessed through black-box evaluations. The outer loop adaptively updates and selects synthetic objectives according to how effectively their induced policies discover promising regions. In contrast, the inner loop returns a portfolio of top-performing policies to reduce the risk of relying on a single surrogate preference. This formulation reframes objective design as a mechanism for guiding policy exploration, enabling the search process to exploit observed evidence while maintaining structured diversity across discrete solution spaces. Extensive experiments across multiple benchmark problems demonstrate that SCOPE consistently improves black-box search performance under limited evaluation budgets and generalizes well across diverse combinatorial structures. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Comments: 43 pages; Kiet, Duc, and Bang contributed equally

RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planning

Authors: Nguyen Viet Tuan Kiet, Bui Dinh Pham, Duong Quoc Chinh, Dao Van Tung, Tran Cong Dao, Huynh Thi Thanh Binh

Abstract: Multi-agent planning becomes substantially harder when agents must improve specialized decision-making skills while keeping their executable implementations private. This setting arises when independently developed agents expose heterogeneous interfaces, observations, and capabilities, yet must coordinate under a shared team objective. Existing approaches commonly rely on centralized optimization,… ▽ More Multi-agent planning becomes substantially harder when agents must improve specialized decision-making skills while keeping their executable implementations private. This setting arises when independently developed agents expose heterogeneous interfaces, observations, and capabilities, yet must coordinate under a shared team objective. Existing approaches commonly rely on centralized optimization, shared policy access, or common skill representations, assumptions that limit knowledge reuse when function signatures differ. We introduce RELIC, a framework for learning interpretable and composable programmatic skills through revealed principles. Each agent improves its own executable skill locally, while useful decision logic and coordination patterns are distilled into compact textual principles. Rather than requiring direct program exchange, these abstractions can be re-instantiated under agent-specific interfaces and reused across incompatible implementation spaces. A shared principle memory accumulates transferable knowledge and promotes abstractions that repeatedly improve team-level performance. This separation allows discoveries made by one agent to guide others while preserving local executable implementations and decentralized execution. RELIC therefore supports strategic transfer across both heterogeneous-role and shared-role cooperative teams. Extensive experiments across routing, scheduling, combinatorial optimization, and distributed coordination settings demonstrate RELIC's effectiveness against independent and joint LLM-based search methods, together with consistent benefits across task structures and LLM backbones. △ Less

Submitted 30 July, 2026; v1 submitted 18 July, 2026; originally announced July 2026.

Comments: v1 accepted at LM4Plan Workshop @ ICML 2026; v2 is the full paper version; Kiet, Pham, and Chinh contributed equally in v2

Safe Bayesian Optimization with Counterfactual Policies

Authors: Katherine Avery, Bruno Castro da Silva, David Jensen

Abstract: In many decision-making settings, new interventions are acceptable only if they do not reduce outcomes below some established threshold. For example, in clinical medicine, new treatments are often acceptable only if they do not worsen outcomes relative to an established standard of care. Safe Bayesian optimization maximizes an objective subject to safety constraints. In the setting that we conside… ▽ More In many decision-making settings, new interventions are acceptable only if they do not reduce outcomes below some established threshold. For example, in clinical medicine, new treatments are often acceptable only if they do not worsen outcomes relative to an established standard of care. Safe Bayesian optimization maximizes an objective subject to safety constraints. In the setting that we consider here, safety is defined relative to a known baseline policy whose outcomes are counterfactual and therefore unobserved. Thus, the counterfactual outcomes of the baseline policy must be estimated and those (uncertain) estimates must be used to safely optimize the objective. We address this estimation problem by using conformal prediction to construct valid uncertainty intervals for counterfactual baseline outcomes, and we show how these intervals can be integrated into safe Bayesian optimization to ensure that constraint violations occur at or below a user-specified rate. We also show how to adapt these conformal estimates to different kinds of covariate shift. We provide a safety proof, experimental evidence, and a sensitivity analysis. △ Less

Submitted 9 August, 2026; v1 submitted 6 July, 2026; originally announced July 2026.

Comments: 10 pages main text, 20 pages total

ACM Class: I.2; G.3; G.1.6

OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement

Authors: Adriana Laurindo Monteiro, Nayse Fagundes, Gabriel Mattos Langeloh, Gustavo de Oliveira Kanno, Priscila Louise Aguirre, Thiago Costa Rizuti da Rocha, Victor Leme Beltran

Abstract: We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-ready mathematical formulation as well as executable code. Our architecture prioritizes the mathematical modeling step, where dedicated agents extract structures, such as decision variables and constraints, enabling iterative self-correction. We int… ▽ More We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-ready mathematical formulation as well as executable code. Our architecture prioritizes the mathematical modeling step, where dedicated agents extract structures, such as decision variables and constraints, enabling iterative self-correction. We introduce a novel multi-loop validation architecture with four specialized feedback mechanisms, each targeting a distinct failure mode such as misinterpretation, structural defects, mathematical inconsistencies, validation failures, and code errors. Alongside accuracy, our modular design improves the process of solving optimization problems by improving transparency, as each agent exposes its reasoning and feedback, making the full modeling process auditable. Our framework achieves state-of-the-art performance on 3 out of 4 benchmarks across LP, MILP, and Nonlinear Programming tasks, while remaining highly competitive on the remaining dataset. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation

Authors: Bertram Taetz, Hugo Albuquerque Cosme da Silva, Gabriele Bleser-Taetz

Abstract: Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M). While foundational models have achieved strong performance in static settings, autonomous agents operating in dynamic environments must continuously incorporate new motion concepts -- such as novel athletic styles or s… ▽ More Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M). While foundational models have achieved strong performance in static settings, autonomous agents operating in dynamic environments must continuously incorporate new motion concepts -- such as novel athletic styles or specialized gestures -- without catastrophic forgetting of previously acquired skills. We investigate the stability-plasticity trade-off in bidirectional motion-language learning under sequential task exposure. Building on a frozen large language model backbone, we introduce low-rank adaptation (LoRA) variants designed to mitigate inter-task interference. We specifically propose mixture-of-experts architectures that utilize an autoencoder-based router to select task-specific experts at inference time, so that no task-label is needed. To evaluate these methods, we establish a reproducible five-task benchmark derived from HumanML3D through semantic clustering of motion descriptions. Our experimental results demonstrate near-zero forgetting across both M2T and T2M directions while maintaining high generation and captioning quality. Furthermore, we show that hard expert selection via routing significantly outperforms soft expert blending in quality metrics, indicating that preserving expert isolation is critical for maintaining performance in our continual learning setting. Finally, we observe that a divergence between token-level accuracy and downstream generation quality may occur, highlighting the need for more comprehensive evaluation protocols in future research on lifelong motion-language agents. △ Less

Submitted 29 June, 2026; originally announced June 2026.

Comments: 16 pages, 1 figure, Accepted at the Conference on Lifelong Learning Agents (CoLLAs) 2026

NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning

Authors: Tianlin Pan, Lianyu Pang, Cheng Da, Huan Yang, Changqian Yu, Kun Gai, Wenhan Luo

Abstract: Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy. We identify a simple structural signature of this drift: across three post-training methods (NFT, AWM, DPO), RL fine-tuning inflates the per-step velocity norm $\|v_θ\|$ by $5\%$ to $15\%$ relative to the referenc… ▽ More Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy. We identify a simple structural signature of this drift: across three post-training methods (NFT, AWM, DPO), RL fine-tuning inflates the per-step velocity norm $\|v_θ\|$ by $5\%$ to $15\%$ relative to the reference. A form of norm inflation has been studied in classifier-free guidance (CFG), where rescaling the velocity back to a reference norm at inference time can mitigate the resulting artifacts. However, this inference-time correction does not transfer cleanly to RL: rescaling $v_θ$ to match $\|v_{\text{ref}}\|$ at inference time neither improves reward nor fixes the quality degradation, because the inflation is co-adapted into the model weights. Furthermore, an adjoint sensitivity analysis shows that velocity magnitude rescaling carries no coherent first-order reward signal at the batch level, indicating that suppressing norm inflation is unlikely to remove a consistently reward-carrying component. Since inference-time renormalization fails while norm suppression carries no reward cost, training-time intervention is the appropriate strategy. Together, these findings motivate NormGuard, a hinge penalty that activates only when $\|v_θ\|$ exceeds $\|v_{\text{ref}}\|$ and composes additively with any velocity-local base loss. Across two base models, three post-training methods, and two reward proxies, NormGuard consistently improves MLLM-judged image quality and forensic realism while preserving reward, with gains that amplify under few-step inference and are not explained by early stopping. △ Less

Submitted 5 August, 2026; v1 submitted 26 June, 2026; originally announced June 2026.

Comments: v5: Fixed PDF rendering compatibility issue affecting Apple PDFKit (macOS Preview/iOS PDF viewer). No changes to technical content compared to v4

A Tool for the Synthesis of Adaptive Probabilistic Processors Based on the Ising Model

Authors: Jonathan Juracy Carneiro da Silva, Leonardo R. Gobatto, Jose Rodrigo Azambuja

Abstract: This work presents a tool for the synthesis and simulation of probabilistic architectures for solving combinatorial optimization problems by mapping them to the Ising model. The proposed approach automatically constructs the Ising Hamiltonian and determines the number of probabilistic elements (p-bits) based on problem characteristics such as size and topology. Furthermore, the tool introduces an… ▽ More This work presents a tool for the synthesis and simulation of probabilistic architectures for solving combinatorial optimization problems by mapping them to the Ising model. The proposed approach automatically constructs the Ising Hamiltonian and determines the number of probabilistic elements (p-bits) based on problem characteristics such as size and topology. Furthermore, the tool introduces an adaptive strategy for selecting the most suitable update algorithm among Gibbs Sampling, Simulated Annealing (SA), Simulated Quantum Annealing (SQA), and cluster-based methods. Experimental results using benchmark problems demonstrate improved convergence behavior and flexibility compared to fixed approaches. The proposed framework enables systematic evaluation of probabilistic computing strategies and supports the development of future hardware implementations based on MTJs and p-bits. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: ACM/IEEE/SBC/SBMICRO Symposium on Integrated Circuits and Systems Design 2026

ACM Class: C.1.3

MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training

Authors: Lianyu Pang, Tianlin Pan, Cheng Da, Changqian Yu, Huan Yang, Kun Gai, Song Guo, Wenhan Luo

Abstract: Representation alignment with pretrained vision models has recently shown strong potential for accelerating diffusion transformer training. By aligning intermediate diffusion features with clean-image representations from self-supervised vision encoders, existing methods improve convergence and generation quality. However, such alignment also introduces a non-trivial constraint: diffusion models o… ▽ More Representation alignment with pretrained vision models has recently shown strong potential for accelerating diffusion transformer training. By aligning intermediate diffusion features with clean-image representations from self-supervised vision encoders, existing methods improve convergence and generation quality. However, such alignment also introduces a non-trivial constraint: diffusion models operate on noisy inputs whose usable information varies across timesteps, while the reference features are extracted from clean images. In this paper, we revisit this mismatch from a token-level perspective. We find that, under full-token representation alignment, tokens with large alignment-gradient norms exhibit a stable spatial preference, suggesting that the alignment objective does not affect all tokens uniformly and may encourage the model to rely on the complete set of clean-image tokens. To address this issue, we propose MaskAlign, a token-subset representation alignment method that applies alignment to randomly sampled token subsets during training. By exposing the model to different token subsets across iterations, MaskAlign reduces the dependence of representation alignment on the complete token set and encourages alignment behavior that is more stable under token-subset perturbations. To mitigate the information loss caused by directly dropping tokens, we further introduce a lightweight pre-mask token mixing block that shares information across tokens before masking. △ Less

Submitted 7 June, 2026; originally announced June 2026.

Cubic graphs, $S$-minors and conformal minors

Authors: Nishad Kothari, Orlando Lee, Cláudio L. Lucchesi, Cândida Nunes da Silva

Abstract: It is well-known that any class of simple graphs, that is characterized by finitely many forbidden minors, also admits a characterization by finitely many forbidden topological minors; furthermore, the list of forbidden topological minors may be derived from the list of forbidden minors. We prove a similar result in Matching Theory. Our Main Theorem states that any class of matching covered grap… ▽ More It is well-known that any class of simple graphs, that is characterized by finitely many forbidden minors, also admits a characterization by finitely many forbidden topological minors; furthermore, the list of forbidden topological minors may be derived from the list of forbidden minors. We prove a similar result in Matching Theory. Our Main Theorem states that any class of matching covered graphs, that is characterized by finitely many forbidden $S$-minors that are cubic, also admits a characterization by finitely many forbidden conformal minors that are cubic as well; once again, the list of forbidden conformal minors may be derived from the list of forbidden $S$-minors. In order to establish the above, we first prove that every matching covered graph has one of two graphs as a conformal minor -- either $K_4$, or the $Θ$ graph (that is, two vertices joined by three edges). (In fact, we need and prove a much stronger statement.) This is reminiscent of a theorem due to Lovász: every nonbipartite matching covered graph has one of two graphs as a conformal minor -- either $K_4$, or the triangular prism $\overline{C_6}$. As applications of our Main Theorem, we deduce known 'forbidden conformal minor characterizations' of pfaffian near-bipartite graphs, and of pfaffian solid graphs, using their respective known 'forbidden $S$-minor characterizations'. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Margin Play: A Multi-Agent System For Public Policy Analysis In The Brazilian Equatorial Margin

Authors: Antonio de Sousa Leitão Filho, Fabrício Saul Lima, Selby Mykael Lima dos Santos, Rejani Bandeira Vieira Sousa, Luís Jorge Mesquita de Jesus, Dennys Correia da Silva, Allan Kardec Duailibe Barros Filho

Abstract: The Brazilian Equatorial Margin (BEM) is Brazil's next offshore oil frontier, with operations expected to begin in 2026 in the Foz do Amazonas basin. Its assets are fiscally and territorially linked primarily to Maranhao -- the state with the lowest HDI in the Federation (0.676, IBGE 2022). This raises the central policy question: under what conditions does BEM exploration generate net positive ex… ▽ More The Brazilian Equatorial Margin (BEM) is Brazil's next offshore oil frontier, with operations expected to begin in 2026 in the Foz do Amazonas basin. Its assets are fiscally and territorially linked primarily to Maranhao -- the state with the lowest HDI in the Federation (0.676, IBGE 2022). This raises the central policy question: under what conditions does BEM exploration generate net positive externalities for Maranhao? The problem is intrinsically multi-agent: the Federal Government seeks revenue and energy security; the state seeks regional welfare under constitutional royalty earmarking; the operator maximizes profit under risk; ANP and IBAMA hold conflicting mandates; and Amazonian communities prioritize territorial and environmental vectors over monetary income. We present Margin Play, a Multi-Agent Reinforcement Learning (MARL) system simulating these tensions under Brazilian empirical calibration and classical economic literature. It implements six agents under the CTDE paradigm, trained with BRO-MARL. Results from 60,000 episodes across six scenarios indicate the answer is conditional on the institutional regime: under the reference baseline, the welfare gain is marginal (Waval approx. 1.68), whereas the MA-Prospero configuration yields Delta W = +17.5% and Delta Rcom = +21.3%, with a lower environmental liability (Eamb = 0.048 vs. 0.076). The fundamental problem is not a trade-off between production and welfare, but the choice of public policy regime linked to exploration. △ Less

Submitted 26 May, 2026; originally announced June 2026.

From Noise to Control: Parameterized Diffusion Policies

Authors: Renhao Zhang, Haotian Fu, Mingxi Jia, George Konidaris, Yilun Du, Bruno Castro da Silva

Abstract: We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior manifold. By constructing this manifold so that distances between latent representations reflect the semantic similarity between physical trajectories, we transform diffusion from a mechanism for stochastic diversity into… ▽ More We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior manifold. By constructing this manifold so that distances between latent representations reflect the semantic similarity between physical trajectories, we transform diffusion from a mechanism for stochastic diversity into a precise and optimizable tool for behavior steering. Our approach enables smooth interpolation between known strategies and efficient adaptation to novel constraints without updating policy weights. We demonstrate that PDP significantly improves adaptation performance on complex multimodal benchmarks in both simulated and real-robot experiments compared to standard diffusion policies, particularly in scenarios requiring the synthesis of novel behaviors. △ Less

Submitted 29 May, 2026; originally announced June 2026.

Hylos: Operability Contracts for Model-Native Spatial Intelligence

Authors: Christopher Da Silva

Abstract: Foundation models can increasingly describe, reconstruct, and generate 3D objects, assemblies, scenes, and environments, but visually plausible spatial output is not yet operable 3D. A generated object or environment becomes useful to an agent only when the system can identify its entities, frames, surfaces, constraints, provenance, admissible actions, expected effects, and validation failures. Th… ▽ More Foundation models can increasingly describe, reconstruct, and generate 3D objects, assemblies, scenes, and environments, but visually plausible spatial output is not yet operable 3D. A generated object or environment becomes useful to an agent only when the system can identify its entities, frames, surfaces, constraints, provenance, admissible actions, expected effects, and validation failures. This paper introduces Hylos, a systems architecture for contract-bounded spatial intelligence. Hylos maintains scene-scale operability state over objects, assemblies, assets, surface anchors, assertions, action candidates, solver jobs, shared actuator invocations, capability gaps, and effect diffs. Durable spatial changes are routed through a SpatialTransaction: a commit boundary that resolves references, checks admissibility, protects invariants, projects effects, and returns commit, review, rollback, deferral, or capability-gap outcomes. The paper is framed as a systems/position preprint with a focused artifact study rather than a broad benchmark. The study examines causal repair: a visible misalignment appears on a dependent component, while the supported repair lies upstream in the placement structure that controls it. The successful interaction traces the symptom through scene dependencies, selects a supported upstream interaction, and applies a validated change instead of directly editing visible geometry. The broader claim is that spatial AI should be evaluated not only by visual quality, but by whether generated or edited 3D can become reliable substrate for CAD, robotics, simulation, inspection, manufacturing, and interactive world authoring. △ Less

Submitted 23 May, 2026; originally announced May 2026.

Comments: 27 pages, 7 figures. Systems/position preprint with focused artifact study

OrganicHAR: Towards Activity Discovery in Organic Settings for Privacy Preserving Sensors Using Efficient Video Analysis

Authors: Prasoon Patidar, Riku Arakawa, Ricardo Graça, Rúben Moutinho, Adriano Soares, Ana Vasconcelos, Filippo Talami, Joana Couto da Silva, Inês Silva, Cristina Mendes Santos, Mayank Goel, Yuvraj Agarwal

Abstract: Deploying human activity recognition (HAR) at home is still rare because sensor signals vary wildly across houses, people, and time, essentially requiring in-situ data collection and training. Prior approaches use cameras to generate training labels for privacy-preserving sensors (LiDAR, RADAR, Thermal), but this forces sensors to detect predefined activities that cameras can see yet the sensors t… ▽ More Deploying human activity recognition (HAR) at home is still rare because sensor signals vary wildly across houses, people, and time, essentially requiring in-situ data collection and training. Prior approaches use cameras to generate training labels for privacy-preserving sensors (LiDAR, RADAR, Thermal), but this forces sensors to detect predefined activities that cameras can see yet the sensors themselves cannot reliably distinguish. In this work, we introduce OrganicHAR, an activity discovery framework that inverts this relationship by placing sensor capabilities at the center of activity discovery. Our approach identifies naturally occurring signal patterns using privacy-preserving sensors, leverages Vision Language Models (VLMs) only during these key moments for scene understanding, and discovers discrete activity labels at granularities that these sensors can reliably detect. Our evaluation with 12 participants demonstrates OrganicHAR's effectiveness: it achieves 79% accuracy for coarse (4-5) activities using only basic ambient sensors (radar, lidar, thermal arrays), and 73% accuracy for fine-grained (8-9) activities when a wearable IMU, depth, and pose sensor are added. OrganicHAR maintains 77% accuracy on average across configurations while discovering 4-8 categories per user (15 across all users) tailored to each environment and sensor capabilities. By triggering video processing only at key moments identified by local sensors, we reduce queries to VLM by 90%, enabling practical and privacy-preserving activity recognition in natural settings. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Comments: 23 pages, 14 figures, with a 4-page appendix containing 2 additional figures. To appear in Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. (IMWUT), Vol. 9, No. 4, Article 203 (December 2025). DOI: 10.1145/3770674

ACM Class: H.5.2; I.2.10; I.5.4

Journal ref: Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 9(4) (2025) 203:1-203:32

Accelerating State-Vector Quantum Simulation on Integrated GPUs via Cache Locality Optimization: A Cross-Architecture Evaluation

Authors: Gabriel Fernandes Thomaz, Jerusa Marchi, Eduarda Rodrigues Monteiro, Fernando Augusto Caletti de Barros, Evandro Chagas Ribeiro da Rosa

Abstract: The classical simulation of quantum algorithms is a crucial tool for circuit development, testing, and validation. Although acceleration using GPUs significantly reduces simulation time, most high-performance simulators rely on vendor-specific frameworks that target data-center hardware. To broaden access to quantum simulation, this work proposes a vendor-agnostic approach targeting the integrated… ▽ More The classical simulation of quantum algorithms is a crucial tool for circuit development, testing, and validation. Although acceleration using GPUs significantly reduces simulation time, most high-performance simulators rely on vendor-specific frameworks that target data-center hardware. To broaden access to quantum simulation, this work proposes a vendor-agnostic approach targeting the integrated GPUs commonly found in consumer-grade laptops. A primary challenge in state-vector simulation is its inherently poor spatial locality, which creates a memory bandwidth bottleneck. Consequently, baseline implementations experience a severe degradation in relative GPU speedup as the number of simulated qubits increases. To address this limitation, we introduce a state partitioning optimization that reorganizes the quantum state vector to maximize the last-level cache locality and minimize costly main memory fetches. We evaluate this strategy using a Quantum Phase Estimation algorithm across diverse architectures from Intel, AMD, and Apple. The experimental results demonstrate that the proposed optimization successfully mitigates performance degradation at larger qubit scales. In particular, for a 28-qubit simulation, the optimization reversed a performance deficit on an Intel Core i5, improving the GPU speedup over the CPU from 0.95x to 1.89x, and increased the Apple M1 Pro speedup from 3.71x to 5.88x. Overall, this approach yields consistent execution time improvements, demonstrating the viability of integrated GPUs for efficient quantum circuit simulation. △ Less

Submitted 14 May, 2026; originally announced May 2026.

MSC Class: 68Q12; 81P68 (Primary) 68W10; 65Y05 (Secondary) ACM Class: C.1.2; C.1.4; F.1.1

Keeping track of errors: A study of SHACL-DS for RDF dataset validation on the ERA RINF Knowledge Graph

Authors: Davan Chiem Dao, Ghislain Atemezing, Christophe Debruyne

Abstract: SHACL-DS extends SHACL for RDF dataset validation by introducing declarative targeting of named graphs and graph combinations, but has not yet been demonstrated and assessed on a real, large-scale Knowledge Graph (KG). In this paper, we apply the SHACL-DS approach to validate its use on such a KG. We apply SHACL-DS to the European Railway Infrastructure (ERA RINF) KG, a large-scale RDF dataset in… ▽ More SHACL-DS extends SHACL for RDF dataset validation by introducing declarative targeting of named graphs and graph combinations, but has not yet been demonstrated and assessed on a real, large-scale Knowledge Graph (KG). In this paper, we apply the SHACL-DS approach to validate its use on such a KG. We apply SHACL-DS to the European Railway Infrastructure (ERA RINF) KG, a large-scale RDF dataset in which 56 infrastructure managers contribute data to dedicated named graphs. We migrate the ERA-RINF shapes to SHACL-DS using two strategies and evaluate their performance using a TopBraid SHACL-DS implementation developed for this study. We compare the performance against the SHACL approach, which "flattens" all graphs into a single data graph. Both strategies produce the same results and are faster than the SHACL baseline. Not only do we demonstrate that SHACL-DS is at least as expressive as SHACL, but SHACL-DS also allows the validation scope to be declared inside the shapes artefact, enforces triple provenance through \texttt{GRAPH} clauses, enriches validation reports with per-graph annotations, and enables shape organisation across named shapes graphs. △ Less

Submitted 11 May, 2026; originally announced May 2026.

Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs

Authors: Nguyen Viet Tuan Kiet, Bui Dinh Pham, Dao Van Tung, Tran Cong Dao, Huynh Thi Thanh Binh

Abstract: Large language models (LLMs) have recently advanced automatic heuristic design (AHD) for combinatorial optimization (CO), where candidate heuristics are iteratively proposed, evaluated, and refined. Most existing approaches search over executable programs and distill insights from execution feedback to guide later iterations. Because this process moves from low-level implementations to high-level… ▽ More Large language models (LLMs) have recently advanced automatic heuristic design (AHD) for combinatorial optimization (CO), where candidate heuristics are iteratively proposed, evaluated, and refined. Most existing approaches search over executable programs and distill insights from execution feedback to guide later iterations. Because this process moves from low-level implementations to high-level principles, we refer to it as a bottom-up paradigm. We argue that this view is incomplete and introduce a complementary top-down perspective: knowledge becomes the primary search object and code merely instantiates and tests it, making what is learned explicit and reusable across problems and trajectories. We formalize this shift through a statistical-learning view that exposes a distortion--compression trade-off, and instantiate it in both population-based and tree-based AHD frameworks. Across CO and tasks beyond it, knowledge-first search improves discovery efficiency, transfer, and generalization, often outperforming code-centric pipelines, while combining both strategies yields further gains. Our results suggest that progress in AHD depends on iteratively constructing and evolving interpretable hypotheses that retain value beyond a single search trajectory. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Comments: 75 pages

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

Authors: Zeyu Liu, Zanlin Ni, Yang Yue, Cheng Da, Huan Yang, Di Zhang, Kun Gai, Gao Huang

Abstract: Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design, while effective for individual tasks, weakens the connection required for mutual enhancement, leaving the potential synergy empirically uncertain. We propose to… ▽ More Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design, while effective for individual tasks, weakens the connection required for mutual enhancement, leaving the potential synergy empirically uncertain. We propose to explicitly restore this synergy by introducing Understanding-Oriented Post-Training (UNO), a lightweight framework that treats understanding not only as a distinct task, but also a direct supervisory signal to steer generative representations. By incorporating objectives that encode semantic abstraction (captioning) and structural details (visual regression), we enable effective gradient flow from understanding to generation. Extensive experiments on image generation and editing demonstrate that understanding can serve as an effective catalyst for generation. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Second-Order FALQON Parameter Transfer for the Max-Cut Problem on 3-Regular Graphs

Authors: Gabriel Fernandes Thomaz, Eduarda Rodrigues Monteiro, Jerusa Marchi, Marcelo Zen Pretto, Alisson dos Passos Fumaco, Evandro Chagas Ribeiro da Rosa

Abstract: The Feedback-based Algorithm for Quantum Optimization (FALQON) offers a deterministic alternative to variational quantum algorithms by bypassing classical optimization loops. However, maintaining convergence on large problem instances often requires restricting the time step, necessitating quantum circuit depths that exceed Noisy Intermediate-Scale Quantum (NISQ) hardware capabilities. This paper… ▽ More The Feedback-based Algorithm for Quantum Optimization (FALQON) offers a deterministic alternative to variational quantum algorithms by bypassing classical optimization loops. However, maintaining convergence on large problem instances often requires restricting the time step, necessitating quantum circuit depths that exceed Noisy Intermediate-Scale Quantum (NISQ) hardware capabilities. This paper investigates the parameter transferability of second-order FALQON applied to the Max-Cut problem on 3-regular graphs. Through numerical experiments evaluating quantum circuits up to 16 layers on graphs up to 24 nodes, we demonstrate a highly advantageous scaling behavior: transferring feedback parameters optimized on small instances to larger target graphs yields significantly higher approximation ratios than natively optimizing the parameters directly on the larger graphs. This performance advantage arises because parameters trained on smaller instances can safely adopt aggressively larger time steps. By offloading the expensive parameter discovery phase to small-scale instances, this transfer strategy simultaneously reduces computational overhead and enhances the approximation ratio, thereby bringing FALQON closer to practical viability on near-term quantum architectures. △ Less

Submitted 5 May, 2026; originally announced May 2026.

From Prompt to Physical Actuation: Holistic Threat Modeling of LLM-Enabled Robotic Systems

Authors: Neha Nagaraja, Hayretdin Bahsi, Carlo R. da Cunha

Abstract: As large language models are integrated into autonomous robotic systems for task planning and control, compromised inputs or unsafe model outputs can propagate through the planning pipeline to physical-world consequences. Although prior work has studied robotic cybersecurity, adversarial perception attacks, and LLM safety independently, no existing study traces how these threat categories interact… ▽ More As large language models are integrated into autonomous robotic systems for task planning and control, compromised inputs or unsafe model outputs can propagate through the planning pipeline to physical-world consequences. Although prior work has studied robotic cybersecurity, adversarial perception attacks, and LLM safety independently, no existing study traces how these threat categories interact and propagate across trust boundaries in a unified architectural model. We address this gap by modeling an LLM-enabled autonomous robot in an edge-cloud architecture as a hierarchical Data Flow Diagram and applying STRIDE-per-interaction analysis across six boundary-crossing interaction points using a three-category taxonomy of Conventional Cyber Threats, Adversarial Threats, and Conversational Threats. The analysis reveals that these categories converge at the same boundary crossings, and we trace three cross-boundary attack chains from external entry points to unsafe physical actuation, each exposing a distinct architectural property: the absence of independent semantic validation between user input and actuator dispatch, cross-modal translation from visual perception to language-model instruction, and unmediated boundary crossing through provider-side tool use. To our knowledge, this is the first DFD-based threat analysis integrating all three threat categories across the full perception-planning-actuation pipeline of an LLM-enabled robotic system. △ Less

Submitted 4 May, 2026; v1 submitted 29 April, 2026; originally announced April 2026.

Comments: Submitted to 23rd Annual International Conference on Privacy, Security, and Trust (PST2026)

Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach

Authors: Flávio Soriano, Victoria F. Mello, Pedro B. Rigueira, Gisele L. Pappa, Wagner Meira Jr., Ana Paula Couto da Silva, Jussara M. Almeida

Abstract: Analyses of legislative behavior often rely on voting records, overlooking the rich semantic and rhetorical content of political speech. In this paper, we ask three complementary questions about parliamentary discourse: how things are said, what is being said, and who is speaking in discursively similar ways. To answer these questions, we introduce a scalable and generalizable computational framew… ▽ More Analyses of legislative behavior often rely on voting records, overlooking the rich semantic and rhetorical content of political speech. In this paper, we ask three complementary questions about parliamentary discourse: how things are said, what is being said, and who is speaking in discursively similar ways. To answer these questions, we introduce a scalable and generalizable computational framework that combines diachronic stylometric analysis, contextual topic modeling, and semantic clustering of deputies' speeches. We apply this framework to a large-scale case study of the Brazilian Chamber of Deputies, using a corpus of over 450,000 speeches from 2003 to 2025. Our results show a long-term stylistic shift toward shorter and more direct speeches, a legislative agenda that reorients sharply in response to national crises, and a granular map of discursive alignments in which regional and gender identities often prove more salient than formal party affiliation. More broadly, this work offers a robust methodology for analyzing parliamentary discourse as a multidimensional phenomenon that complements traditional vote-based approaches. △ Less

Submitted 23 April, 2026; originally announced April 2026.

Comments: Accepted paper at ICWSM 2026

DR. INFO at the Point of Care: A Prospective Pilot Study of Physician-Perceived Value of an Agentic AI Clinical Assistant

Authors: Rogerio Corga Da Silva, Miguel Romano, Tiago Mendes, Marta Isidoro, Sandhanakrishnan Ravichandran, Shivesh Kumar, Michiel van der Heijden, Olivier Fail, Valentine Emmanuel Gnanapragasam

Abstract: Background: Clinical documentation and information retrieval consume over half of physicians working hours, contributing to cognitive overload and burnout. While artificial intelligence offers a potential solution, concerns over hallucinations and source reliability have limited adoption at the point of care. This study aimed to evaluate physician-perceived time efficiency, decision-making support… ▽ More Background: Clinical documentation and information retrieval consume over half of physicians working hours, contributing to cognitive overload and burnout. While artificial intelligence offers a potential solution, concerns over hallucinations and source reliability have limited adoption at the point of care. This study aimed to evaluate physician-perceived time efficiency, decision-making support, and satisfaction with DR. INFO, an agentic AI clinical assistant, in routine clinical practice. Methodology: In this prospective, single-arm, pilot feasibility study, 29 physicians and medical students across multiple specialties in Portuguese healthcare institutions used DR. INFO v1.0 over five working days within a two-week period. Outcomes were assessed via daily Likert-scale evaluations (time saving and decision support) and a final Net Promoter Score (NPS). Non-parametric methods were used throughout, with bootstrap confidence intervals (CIs) and sensitivity analysis to address non-response. Results: Physicians reported high perceived time saving (mean = 4.27/5; 95% CI = 3.97-4.57) and decision support (mean = 4.16/5; 95% CI = 3.86-4.45), with ratings stable across the five-day study window. Among the 16 (55%) participants who completed the final evaluation, the NPS was 81.2, with no detractors; sensitivity analysis indicated an NPS of 44.8 under conservative non-response assumptions. Conclusions: Physicians across specialties and career stages reported positive perceptions of DR. INFO for both time efficiency and clinical decision support within the study window. These findings are preliminary and should be confirmed in larger, controlled studies that include objective performance measures and independent accuracy verification. △ Less

Submitted 22 April, 2026; v1 submitted 16 March, 2026; originally announced April 2026.

Orthogonality between acyclic subdigraphs and paths in digraphs

Authors: Caroline A. de Paula Silva, Cândida Nunes da Silva, Orlando Lee

Abstract: Let $D$ be a digraph. A collection of disjoint sets of vertices (respec., collection of disjoint subdigraphs) $\mathcal{H}$ of $D$ and a vertex subset (or subdigraph) $Q$ of $D$ are orthogonal if every set (respec., subdigraph) $H \in \mathcal{H}$ contains exactly one vertex of $Q$. A well-known result of Gallai and Milgram shows that for every minimum path partition of a digraph there is a stable… ▽ More Let $D$ be a digraph. A collection of disjoint sets of vertices (respec., collection of disjoint subdigraphs) $\mathcal{H}$ of $D$ and a vertex subset (or subdigraph) $Q$ of $D$ are orthogonal if every set (respec., subdigraph) $H \in \mathcal{H}$ contains exactly one vertex of $Q$. A well-known result of Gallai and Milgram shows that for every minimum path partition of a digraph there is a stable set orthogonal to it. Similarly, Gallai, Hasse, Roy and Vitaver independently proved that for every longest path of a digraph there is a vertex partition into stable sets (i.e, vertex-coloring) orthogonal to it. Berge showed that no analogous statements hold when optimality is required for the stable set or the vertex coloring. In this paper, we show that this holds if we replace stable sets by induced acyclic subdigraphs. In 1981, Linial proposed two generalizations of Gallai-Milgram and Gallai-Hasse-Roy-Vitaver results using a positive integer $k$ as a measure of optimality for the path partition and the coloring, respectively. These generalizations have led to two conjectures that remain open. Using the same strategy of replacing stable sets by induced acyclic subdigraphs, we prove relaxations of both conjectures. △ Less

Submitted 11 May, 2026; v1 submitted 17 March, 2026; originally announced March 2026.

Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning

Authors: Matheus Camilo da Silva, Gabriel Gustavo Costanzo, Andrea de Lorenzo, Sylvio Barbon Junior

Abstract: Many machine learning classification tasks involve imbalanced datasets, which are often subject to over-sampling techniques aimed at improving model performance. However, these techniques are prone to generating unrealistic or infeasible samples. Furthermore, they often function as black boxes, lacking interpretability in their procedures. This opacity makes it difficult to track their effectivene… ▽ More Many machine learning classification tasks involve imbalanced datasets, which are often subject to over-sampling techniques aimed at improving model performance. However, these techniques are prone to generating unrealistic or infeasible samples. Furthermore, they often function as black boxes, lacking interpretability in their procedures. This opacity makes it difficult to track their effectiveness and provide necessary adjustments, and they may ultimately fail to yield significant performance improvements. To bridge this gap, we introduce the Decision Predicate Graphs for Data Augmentation (DPG-da), a framework that extracts interpretable decision predicates from trained models to capture domain rules and enforce them during sample generation. This design ensures that over-sampled data remain diverse, constraint-satisfying, and interpretable. In experiments on synthetic and real-world benchmark datasets, DPG-da consistently improves classification performance over traditional over-sampling methods, while guaranteeing logical validity and offering clear, interpretable explanations of the over-sampled data. △ Less

Submitted 14 March, 2026; originally announced March 2026.

Explaining AutoClustering: Uncovering Meta-Feature Contribution in AutoML for Clustering

Authors: Matheus Camilo da Silva, Leonardo Arrighi, Ana Carolina Lorena, Sylvio Barbon Junior

Abstract: AutoClustering methods aim to automate unsupervised learning tasks, including algorithm selection (AS), hyperparameter optimization (HPO), and pipeline synthesis (PS), by often leveraging meta-learning over dataset meta-features. While these systems often achieve strong performance, their recommendations are often difficult to justify: the influence of dataset meta-features on algorithm and hyperp… ▽ More AutoClustering methods aim to automate unsupervised learning tasks, including algorithm selection (AS), hyperparameter optimization (HPO), and pipeline synthesis (PS), by often leveraging meta-learning over dataset meta-features. While these systems often achieve strong performance, their recommendations are often difficult to justify: the influence of dataset meta-features on algorithm and hyperparameter choices is typically not exposed, limiting reliability, bias diagnostics, and efficient meta-feature engineering. This limits reliability and diagnostic insight for further improvements. In this work, we investigate the explainability of the meta-models in AutoClustering. We first review 22 existing methods and organize their meta-features into a structured taxonomy. We then apply a global explainability technique (i.e., Decision Predicate Graphs) to assess feature importance within meta-models from selected frameworks. Finally, we use local explainability tools such as SHAP (SHapley Additive exPlanations) to analyse specific clustering decisions. Our findings highlight consistent patterns in meta-feature relevance, identify structural weaknesses in current meta-learning strategies that can distort recommendations, and provide actionable guidance for more interpretable Automated Machine Learning (AutoML) design. This study therefore offers a practical foundation for increasing decision transparency in unsupervised learning automation. △ Less

Submitted 20 February, 2026; originally announced February 2026.

Enabling Option Learning in Sparse Rewards with Hindsight Experience Replay

Authors: Gabriel Romio, Mateus Begnini Melchiades, Bruno Castro da Silva, Gabriel de Oliveira Ramos

Abstract: Hierarchical Reinforcement Learning (HRL) frameworks like Option-Critic (OC) and Multi-updates Option Critic (MOC) have introduced significant advancements in learning reusable options. However, these methods underperform in multi-goal environments with sparse rewards, where actions must be linked to temporally distant outcomes. To address this limitation, we first propose MOC-HER, which integrate… ▽ More Hierarchical Reinforcement Learning (HRL) frameworks like Option-Critic (OC) and Multi-updates Option Critic (MOC) have introduced significant advancements in learning reusable options. However, these methods underperform in multi-goal environments with sparse rewards, where actions must be linked to temporally distant outcomes. To address this limitation, we first propose MOC-HER, which integrates the Hindsight Experience Replay (HER) mechanism into the MOC framework. By relabeling goals from achieved outcomes, MOC-HER can solve sparse reward environments that are intractable for the original MOC. However, this approach is insufficient for object manipulation tasks, where the reward depends on the object reaching the goal rather than on the agent's direct interaction. This makes it extremely difficult for HRL agents to discover how to interact with these objects. To overcome this issue, we introduce Dual Objectives Hindsight Experience Replay (2HER), a novel extension that creates two sets of virtual goals. In addition to relabeling goals based on the object's final state (standard HER), 2HER also generates goals from the agent's effector positions, rewarding the agent for both interacting with the object and completing the task. Experimental results in robotic manipulation environments show that MOC-2HER achieves success rates of up to 90%, compared to less than 11% for both MOC and MOC-HER. These results highlight the effectiveness of our dual objective relabeling strategy in sparse reward, multi-goal tasks. △ Less

Submitted 14 February, 2026; originally announced February 2026.

Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration

Authors: Manh Cuong Dao, Quang Hung Pham, Phi Le Nguyen, Thao Nguyen Truong, Bryan Kian Hsiang Low, Trong Nghia Hoang

Abstract: Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty propagation through their feature transformation stack. In this work, we propose a diffusion-inspired reconfiguration of transformers in which each feature transformation block is… ▽ More Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty propagation through their feature transformation stack. In this work, we propose a diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping. Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution. This probability path can then be recompiled on a diffusion process with a unified transition model to enable principled propagation of representation uncertainty throughout the pre-trained model's architecture while maintaining its original predictive performance. Empirical results across a variety of vision and language benchmarks demonstrate that our method achieves superior calibration and predictive accuracy compared to existing uncertainty-aware transformers. △ Less

Submitted 12 May, 2026; v1 submitted 9 February, 2026; originally announced February 2026.

Spot-Wise Smart Parking: An Edge-Enabled Architecture with YOLOv11 and Digital Twin Integration

Authors: Gustavo P. C. P. da Luz, Alvaro M. Aspilcueta Narvaez, Tiago Godoi Bannwart, Gabriel Massuyoshi Sato, Luis Fernando Gomez Gonzalez, Juliana Freitag Borin

Abstract: Smart parking systems help reduce congestion and minimize users' search time, thereby contributing to smart city adoption and enhancing urban mobility. In previous works, we presented a system developed on a university campus to monitor parking availability by estimating the number of free spaces from vehicle counts within a region of interest. Although this approach achieved good accuracy, it res… ▽ More Smart parking systems help reduce congestion and minimize users' search time, thereby contributing to smart city adoption and enhancing urban mobility. In previous works, we presented a system developed on a university campus to monitor parking availability by estimating the number of free spaces from vehicle counts within a region of interest. Although this approach achieved good accuracy, it restricted the system's ability to provide spot-level insights and support more advanced applications. To overcome this limitation, we extend the system with a spot-wise monitoring strategy based on a distance-aware matching method with spatial tolerance, enhanced through an Adaptive Bounding Box Partitioning method for challenging spaces. The proposed approach achieves a balanced accuracy of 98.80% while maintaining an inference time of 8 seconds on a resource-constrained edge device, enhancing the capabilities of YOLOv11m, a model that has a size of 40.5 MB. In addition, two new components were introduced: (i) a Digital Shadow that visually represents parking lot entities as a base to evolve to a full Digital Twin, and (ii) an application support server based on a repurposed TV box. The latter not only enables scalable communication among cloud services, the parking totem, and a bot that provides detailed spot occupancy statistics, but also promotes hardware reuse as a step towards greater sustainability. △ Less

Submitted 2 February, 2026; originally announced February 2026.

Comments: Submitted to Journal of Internet Services and Applications, 27 pages, 20 figures, 3 tables

Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting

Authors: Trong Khiem Tran, Manh Cuong Dao, Phi Le Nguyen, Thao Nguyen Truong, Trong Nghia Hoang

Abstract: Adapting pre-trained models to unseen feature modalities has become increasingly important due to the growing need for cross-disciplinary knowledge integration. A key challenge here is how to align the representation of new modalities with the most relevant parts of the pre-trained model's representation space to enable accurate knowledge transfer. This requires combining feature alignment with ta… ▽ More Adapting pre-trained models to unseen feature modalities has become increasingly important due to the growing need for cross-disciplinary knowledge integration. A key challenge here is how to align the representation of new modalities with the most relevant parts of the pre-trained model's representation space to enable accurate knowledge transfer. This requires combining feature alignment with target fine-tuning, but uncalibrated combinations can exacerbate misalignment between the source and target feature-label structures and reduce target generalization. Existing work, however, lacks a theoretical understanding of this critical interaction between feature alignment and target fitting. To bridge this gap, we develop a principled framework that establishes a provable generalization bound on the target error, which explains the interaction between feature alignment and target fitting through a novel concept of feature-label distortion. This bound offers actionable insights into how this interaction should be optimized for practical algorithm design. The resulting approach achieves significantly improved performance over state-of-the-art methods across a wide range of benchmark datasets. △ Less

Submitted 20 April, 2026; v1 submitted 26 January, 2026; originally announced January 2026.

Comments: Accepted AISTATS 20226

Honesty-Aware Multi-Agent Framework for High-Fidelity Synthetic Data Generation in Digital Psychiatric Intake Doctor-Patient Interactions

Authors: Xinyuan Zhang, Zijian Wang, Chang Dao, Juexiao Zhou

Abstract: Data scarcity and unreliable self-reporting -- such as concealment or exaggeration -- pose fundamental challenges to psychiatric intake and assessment. We propose a multi-agent synthesis framework that explicitly models patient deception to generate high-fidelity, publicly releasable synthetic psychiatric intake records. Starting from DAIC-WOZ interviews, we construct enriched patient profiles and… ▽ More Data scarcity and unreliable self-reporting -- such as concealment or exaggeration -- pose fundamental challenges to psychiatric intake and assessment. We propose a multi-agent synthesis framework that explicitly models patient deception to generate high-fidelity, publicly releasable synthetic psychiatric intake records. Starting from DAIC-WOZ interviews, we construct enriched patient profiles and simulate a four-role workflow: a \emph{Patient} completes self-rated scales and participates in a semi-structured interview under a topic-dependent honesty state; an \emph{Assessor} selects instruments based on demographics and chief complaints; an \emph{Evaluator} conducts the interview grounded in rater-administered scales, tracks suspicion, and completes ratings; and a \emph{Diagnostician} integrates all evidence into a diagnostic summary. Each case links the patient profile, self-rated and rater-administered responses, interview transcript, diagnostic summary, and honesty state. We validate the framework through four complementary evaluations: diagnostic consistency and severity grading, chain-of-thought ablations, human evaluation of clinical realism and dishonesty modeling, and LLM-based comparative evaluation. The resulting corpus spans multiple disorders and severity levels, enabling controlled study of dishonesty-aware psychiatric assessment and the training and evaluation of adaptive dialogue agents. △ Less

Submitted 14 January, 2026; originally announced January 2026.

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation

Authors: Xu Zhang, Cheng Da, Huan Yang, Kun Gai, Ming Lu, Zhan Ma

Abstract: Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent tokens and treating visual data as flat sequential token streams. However, this language-like formulation overlooks key properties of vision, particularly the hie… ▽ More Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent tokens and treating visual data as flat sequential token streams. However, this language-like formulation overlooks key properties of vision, particularly the hierarchical and residual network designs that have long been essential for convergence and efficiency in visual models. To bring "vision" back to vision, we propose the Residual Tokenizer (ResTok), a 1D visual tokenizer that builds hierarchical residuals for both image tokens and latent tokens. The hierarchical representations obtained through progressively merging enable cross-level feature fusion at each layer, substantially enhancing representational capacity. Meanwhile, the semantic residuals between hierarchies prevent information overlap, yielding more concentrated latent distributions that are easier for AR modeling. Cross-level bindings consequently emerge without any explicit constraints. To accelerate the generation process, we further introduce a hierarchical AR generator that substantially reduces sampling steps by predicting an entire level of latent tokens at once rather than generating them strictly token-by-token. Extensive experiments demonstrate that restoring hierarchical residual priors in visual tokenization significantly improves AR image generation, achieving a gFID of 2.34 on ImageNet-256 with only 9 sampling steps. Code is available at https://github.com/Kwai-Kolors/ResTok. △ Less

Submitted 7 January, 2026; originally announced January 2026.

Comments: Technical report

Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions

Authors: Itallo Patrick Castro Alves Da Silva, Emanuel Adler Medeiros Pereira, Erick de Andrade Barboza, Baldoino Fonseca dos Santos Neto, Marcio de Medeiros Ribeiro

Abstract: Compressed deep learning models are crucial for deploying computer vision systems on resource-constrained devices. However, model compression may affect robustness, especially under natural corruption. Therefore, it is important to consider robustness evaluation while validating computer vision systems. This paper presents a comprehensive evaluation of compression techniques - quantization, prunin… ▽ More Compressed deep learning models are crucial for deploying computer vision systems on resource-constrained devices. However, model compression may affect robustness, especially under natural corruption. Therefore, it is important to consider robustness evaluation while validating computer vision systems. This paper presents a comprehensive evaluation of compression techniques - quantization, pruning, and weight clustering applied individually and in combination to convolutional neural networks (ResNet-50, VGG-19, and MobileNetV2). Using the CIFAR-10-C and CIFAR 100-C datasets, we analyze the trade-offs between robustness, accuracy, and compression ratio. Our results show that certain compression strategies not only preserve but can also improve robustness, particularly on networks with more complex architectures. Utilizing multiobjective assessment, we determine the best configurations, showing that customized technique combinations produce beneficial multi-objective results. This study provides insights into selecting compression methods for robust and efficient deployment of models in corrupted real-world environments. △ Less

Submitted 31 December, 2025; originally announced December 2025.

Comments: Accepted for publication at the 2025 International Conference on Machine Learning and Applications (ICMLA). IEEE Catalog Number: CFP25592-ART

From Code to Field: Evaluating the Robustness of Convolutional Neural Networks for Disease Diagnosis in Mango Leaves

Authors: Gabriel Vitorino de Andrade, Saulo Roberto dos Santos, Itallo Patrick Castro Alves da Silva, Emanuel Adler Medeiros Pereira, Erick de Andrade Barboza

Abstract: The validation and verification of artificial intelligence (AI) models through robustness assessment are essential to guarantee the reliable performance of intelligent systems facing real-world challenges, such as image corruptions including noise, blurring, and weather variations. Despite the global importance of mango (Mangifera indica L.), there is a lack of studies on the robustness of models… ▽ More The validation and verification of artificial intelligence (AI) models through robustness assessment are essential to guarantee the reliable performance of intelligent systems facing real-world challenges, such as image corruptions including noise, blurring, and weather variations. Despite the global importance of mango (Mangifera indica L.), there is a lack of studies on the robustness of models for the diagnosis of disease in its leaves. This paper proposes a methodology to evaluate convolutional neural networks (CNNs) under adverse conditions. We adapted the MangoLeafDB dataset, generating MangoLeafDB-C with 19 types of artificial corruptions at five severity levels. We conducted a benchmark comparing five architectures: ResNet-50, ResNet-101, VGG-16, Xception, and LCNN (the latter being a lightweight architecture designed specifically for mango leaf diagnosis). The metrics include the F1 score, the corruption error (CE) and the relative mean corruption error (relative mCE). The results show that LCNN outperformed complex models in corruptions that can be present in real-world scenarios such as Defocus Blur, Motion Blur, while also achieving the lowest mCE. Modern architectures (e.g., ResNet-101) exhibited significant performance degradation in corrupted scenarios, despite their high accuracy under ideal conditions. These findings suggest that lightweight and specialized models may be more suitable for real-world applications in edge devices, where robustness and efficiency are critical. The study highlights the need to incorporate robustness assessments in the development of intelligent systems for agriculture, particularly in regions with technological limitations. △ Less

Submitted 15 December, 2025; originally announced December 2025.

Comments: This work was presented at the BRACIS 2025 conference in Fortaleza

AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning

Authors: Mansi Maheshwari, John C. Raisbeck, Bruno Castro da Silva

Abstract: Artificial neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from new experiences declines over time. This decline in learning ability is known as plasticity loss. To restore plasticity, prior work has explored period… ▽ More Artificial neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from new experiences declines over time. This decline in learning ability is known as plasticity loss. To restore plasticity, prior work has explored periodically resetting the parameters of the learning network, a strategy that often improves performance. However, such resets come at the cost of a temporary drop in performance, which can be dangerous in real-world settings. To overcome this instability, we introduce AltNet, a reset-based approach that restores plasticity without performance degradation by leveraging a pair of twin networks. The use of twin networks anchors performance during resets through a mechanism that allows networks to periodically alternate roles: one network learns as it acts in the environment, while the other learns off-policy from the active network's interactions through a replay buffer. At fixed intervals, the active network is reset and the passive network, having learned from prior experience, becomes the new active network. AltNet restores plasticity, improving sample efficiency and achieving higher performance, while avoiding performance drops that pose risks in safety-critical settings. We demonstrate these advantages in several high-dimensional control tasks from the DeepMind Control Suite, where AltNet outperforms various relevant baseline methods, as well as state-of-the-art reset-based techniques. △ Less

Submitted 9 March, 2026; v1 submitted 30 November, 2025; originally announced December 2025.

PET Rapid Image Reconstruction Challenge (PETRIC)

Authors: Casper da Costa-Luis, Matthias J. Ehrhardt, Christoph Kolbitsch, Evgueni Ovtchinnikov, Edoardo Pasca, Kris Thielemans, Charalampos Tsoumpas

Abstract: Introduction: We describe the foundation of PETRIC, an image reconstruction challenge to minimise the computational runtime of related algorithms for Positron Emission Tomography (PET). Purpose: Although several similar challenges are well-established in the field of medical imaging, there have been no prior challenges for PET image reconstruction. Methods: Participants are provided with open-… ▽ More Introduction: We describe the foundation of PETRIC, an image reconstruction challenge to minimise the computational runtime of related algorithms for Positron Emission Tomography (PET). Purpose: Although several similar challenges are well-established in the field of medical imaging, there have been no prior challenges for PET image reconstruction. Methods: Participants are provided with open-source software for implementation of their reconstruction algorithm(s). We define the objective function and reconstruct "gold standard" reference images, and provide metrics for quantifying algorithmic performance. We also received and curated phantom datasets (acquired with different scanners, radionuclides, and phantom types), which we further split into training and evaluation datasets. The automated computational framework of the challenge is released as open-source software. Results: Four teams with nine algorithms in total participated in the challenge. Their contributions made use of various tools from optimisation theory including preconditioning, stochastic gradients, and artificial intelligence. While most of the submitted approaches appear very similar in nature, their specific implementation lead to a range of algorithmic performance. Conclusion: As the first challenge for PET image reconstruction, PETRIC's solid foundations allow researchers to reuse its framework for evaluating new and existing image reconstruction methods on new or existing datasets. Variant versions of the challenge have and will continue to be launched in the future. △ Less

Submitted 27 March, 2026; v1 submitted 27 November, 2025; originally announced November 2025.

Journal ref: Front. Nucl. Med. 2026. 6:1770002.

PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz Optimization

Authors: Mingzhe Li, Renhao Zhang, Zhiyang Wen, Siqi Pan, Bruno Castro da Silva, Juan Zhai, Shiqing Ma

Abstract: Text-to-image (T2I) generative models such as Stable Diffusion and FLUX can synthesize realistic, high-quality images directly from textual prompts. The resulting image quality depends critically on well-crafted prompts that specify both subjects and stylistic modifiers, which have become valuable digital assets. However, the rising value and ubiquity of high-quality prompts expose them to securit… ▽ More Text-to-image (T2I) generative models such as Stable Diffusion and FLUX can synthesize realistic, high-quality images directly from textual prompts. The resulting image quality depends critically on well-crafted prompts that specify both subjects and stylistic modifiers, which have become valuable digital assets. However, the rising value and ubiquity of high-quality prompts expose them to security and intellectual-property risks. One key threat is the prompt stealing attack, i.e., the task of recovering the textual prompt that generated a given image. Prompt stealing enables unauthorized extraction and reuse of carefully engineered prompts, yet it can also support beneficial applications such as data attribution, model provenance analysis, and watermarking validation. Existing approaches often assume white-box gradient access, require large-scale labeled datasets for supervised training, or rely solely on captioning without explicit optimization, limiting their practicality and adaptability. To address these challenges, we propose PROMPTMINER, a black-box prompt stealing framework that decouples the task into two phases: (1) a reinforcement learning-based optimization phase to reconstruct the primary subject, and (2) a fuzzing-driven search phase to recover stylistic modifiers. Experiments across multiple datasets and diffusion backbones demonstrate that PROMPTMINER achieves superior results, with CLIP similarity up to 0.958 and textual alignment with SBERT up to 0.751, surpassing all baselines. Even when applied to in-the-wild images with unknown generators, it outperforms the strongest baseline by 7.5 percent in CLIP similarity, demonstrating better generalization. Finally, PROMPTMINER maintains strong performance under defensive perturbations, highlighting remarkable robustness. Code: https://github.com/aaFrostnova/PromptMiner △ Less

Submitted 27 November, 2025; originally announced November 2025.

Reducing Instability in Synthetic Data Evaluation with a Super-Metric in MalDataGen

Authors: Anna Luiza Gomes da Silva, Diego Kreutz, Angelo Diniz, Rodrigo Mansilha, Celso Nobre da Fonseca

Abstract: Evaluating the quality of synthetic data remains a persistent challenge in the Android malware domain due to instability and the lack of standardization among existing metrics. This work integrates into MalDataGen a Super-Metric that aggregates eight metrics across four fidelity dimensions, producing a single weighted score. Experiments involving ten generative models and five balanced datasets de… ▽ More Evaluating the quality of synthetic data remains a persistent challenge in the Android malware domain due to instability and the lack of standardization among existing metrics. This work integrates into MalDataGen a Super-Metric that aggregates eight metrics across four fidelity dimensions, producing a single weighted score. Experiments involving ten generative models and five balanced datasets demonstrate that the Super-Metric is more stable and consistent than traditional metrics, exhibiting stronger correlations with the actual performance of classifiers. △ Less

Submitted 20 November, 2025; originally announced November 2025.

Comments: 5 pages, 3 figures, submitted to ERRC/WRSeg 2025

MSC Class: 68T01 ACM Class: I.2

CURENet: Combining Unified Representations for Efficient Chronic Disease Prediction

Authors: Cong-Tinh Dao, Nguyen Minh Thao Phan, Jun-En Ding, Chenwei Wu, David Restrepo, Dongsheng Luo, Fanyi Zhao, Chun-Chieh Liao, Wen-Chih Peng, Chi-Te Wang, Pei-Fu Chen, Ling Chen, Xinglong Ju, Feng Liu, Fang-Ming Hung

Abstract: Electronic health records (EHRs) are designed to synthesize diverse data types, including unstructured clinical notes, structured lab tests, and time-series visit data. Physicians draw on these multimodal and temporal sources of EHR data to form a comprehensive view of a patient's health, which is crucial for informed therapeutic decision-making. Yet, most predictive models fail to fully capture t… ▽ More Electronic health records (EHRs) are designed to synthesize diverse data types, including unstructured clinical notes, structured lab tests, and time-series visit data. Physicians draw on these multimodal and temporal sources of EHR data to form a comprehensive view of a patient's health, which is crucial for informed therapeutic decision-making. Yet, most predictive models fail to fully capture the interactions, redundancies, and temporal patterns across multiple data modalities, often focusing on a single data type or overlooking these complexities. In this paper, we present CURENet, a multimodal model (Combining Unified Representations for Efficient chronic disease prediction) that integrates unstructured clinical notes, lab tests, and patients' time-series data by utilizing large language models (LLMs) for clinical text processing and textual lab tests, as well as transformer encoders for longitudinal sequential visits. CURENet has been capable of capturing the intricate interaction between different forms of clinical data and creating a more reliable predictive model for chronic illnesses. We evaluated CURENet using the public MIMIC-III and private FEMH datasets, where it achieved over 94\% accuracy in predicting the top 10 chronic conditions in a multi-label framework. Our findings highlight the potential of multimodal EHR integration to enhance clinical decision-making and improve patient outcomes. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback

Authors: Shreyas Chaudhari, Renhao Zhang, Philip S. Thomas, Bruno Castro da Silva

Abstract: The ability of reinforcement learning algorithms to learn effective policies is determined by the rewards available during training. However, for practical problems, obtaining large quantities of reward labels is often infeasible due to computational or financial constraints, particularly when relying on human feedback. When reinforcement learning must proceed with limited feedback -- only a fract… ▽ More The ability of reinforcement learning algorithms to learn effective policies is determined by the rewards available during training. However, for practical problems, obtaining large quantities of reward labels is often infeasible due to computational or financial constraints, particularly when relying on human feedback. When reinforcement learning must proceed with limited feedback -- only a fraction of samples get rewards labeled -- a fundamental question arises: which samples should be labeled to maximize policy performance? We formalize this problem of reward selection for reinforcement learning from limited feedback (RLLF), introducing a new problem formulation that facilitates the study of strategies for selecting impactful rewards. Two types of selection strategies are investigated: (i) heuristics that rely on reward-free information such as state visitation and partial value functions, and (ii) strategies pre-trained using auxiliary evaluative feedback. We find that critical subsets of rewards are those that (1) guide the agent along optimal trajectories, and (2) support recovery toward near-optimal behavior after deviations. Effective selection methods yield near-optimal policies with significantly fewer reward labels than full supervision, establishing reward selection as a powerful paradigm for scaling reinforcement learning in feedback-limited settings. △ Less

Submitted 30 September, 2025; originally announced October 2025.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Authors: Johannes Schmitt, Gergely Bérczi, Jasper Dekoninck, Jeremy Feusi, Tim Gehrunger, Raphael Appenzeller, Pieter Belmans, Alessio Bottini, Jim Bryan, João Camarneiro, Ana Cannas da Silva, Niklas Canova, Ana-Maria Castravet, Timo de Wolff, Claudio Fontanari, Filippo Gaia, Baran Hashemi, Daniel Holmes, David Holmes, Aitor Iribar Lopez, Victor Jaeck, Martina Jørgensen, Steven Kelk, Martijn Kool, Stefan Kuhlmann , et al. (35 additional authors not shown)

Abstract: As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of mathematical knowledge. However, existing benchmarks are limited, as they focus solely on final-answer questions or high-school competition problems. To address this gap, we introduce IMProofBench, a private benchmark c… ▽ More As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of mathematical knowledge. However, existing benchmarks are limited, as they focus solely on final-answer questions or high-school competition problems. To address this gap, we introduce IMProofBench, a private benchmark consisting of 77 peer-reviewed problems developed by expert mathematicians. Each problem requires a detailed proof and is paired with subproblems that have final answers, supporting both an evaluation by human experts and a large-scale quantitative analysis through automated grading. Furthermore, unlike prior benchmarks, the evaluation setup simulates a realistic research environment: models operate in an agentic framework with tools like web search for literature review and mathematical software such as SageMath. Our results show that current LLMs can already solve a significant percentage of research-level questions. IMProofBench will continue to evolve as a dynamic benchmark in collaboration with the mathematical community, ensuring its relevance for evaluating the next generation of LLMs. △ Less

Submitted 9 July, 2026; v1 submitted 30 September, 2025; originally announced September 2025.

Comments: v2: benchmark expanded from 39 to 77 problems; evaluation extended to 14 models including GPT-5.4, Gemini 3.1 Pro, and Claude Opus 4.6; new analyses (IRT-based score aggregation, inter-rater reliability, tool/token usage, non-agentic ablation); contributor author list updated

Exploring AI Capabilities in Participatory Budgeting within Smart Cities: The Case of Sao Paulo

Authors: Italo Alberto Sousa, Mariana Carvalho da Silva, Jorge Machado, José Carlos Vaz

Abstract: This research examines how Artificial Intelligence (AI) can improve participatory budgeting processes within smart cities. In response to challenges like declining civic participation and resource allocation conflicts, the study explores how online political participation can be improved by AI. It investigates the state capacity governments need to implement AI-enhanced participatory tools, consid… ▽ More This research examines how Artificial Intelligence (AI) can improve participatory budgeting processes within smart cities. In response to challenges like declining civic participation and resource allocation conflicts, the study explores how online political participation can be improved by AI. It investigates the state capacity governments need to implement AI-enhanced participatory tools, considering technological dependencies and vulnerabilities. It analyzes technological and administrative structures, actors, interests, and strategies to understand the dynamics of online political participation technologies in the case of Sao Paulo, Brazil. The study contributes to understanding how technological advancements can reshape participatory budgeting processes. In a broader sense, the research highlights how AI can transform participatory institutions by offering new tools for citizens and also for government officials in charge of participatory processes within smart cities. △ Less

Submitted 20 September, 2025; originally announced September 2025.

Comments: 22 pages, Presented at 28th IPSA World Congress of Political Science, Seoul 2025

ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge

Authors: Manh Cuong Dao, The Hung Tran, Phi Le Nguyen, Thao Nguyen Truong, Trong Nghia Hoang

Abstract: This paper studies the black-box optimization task which aims to find the maxima of a black-box function using a static set of its observed input-output pairs. This is often achieved via learning and optimizing a surrogate function with that offline data. Alternatively, it can also be framed as an inverse modeling task that maps a desired performance to potential input candidates that achieve it.… ▽ More This paper studies the black-box optimization task which aims to find the maxima of a black-box function using a static set of its observed input-output pairs. This is often achieved via learning and optimizing a surrogate function with that offline data. Alternatively, it can also be framed as an inverse modeling task that maps a desired performance to potential input candidates that achieve it. Both approaches are constrained by the limited amount of offline data. To mitigate this limitation, we introduce a new perspective that casts offline optimization as a distributional translation task. This is formulated as learning a probabilistic bridge transforming an implicit distribution of low-value inputs (i.e., offline data) into another distribution of high-value inputs (i.e., solution candidates). Such probabilistic bridge can be learned using low- and high-value inputs sampled from synthetic functions that resemble the target function. These synthetic functions are constructed as the mean posterior of multiple Gaussian processes fitted with different parameterizations on the offline data, alleviating the data bottleneck. The proposed approach is evaluated on an extensive benchmark comprising most recent methods, demonstrating significant improvement and establishing a new state-of-the-art performance. Our code is publicly available at https://github.com/cuong-dm/ROOT. △ Less

Submitted 23 October, 2025; v1 submitted 19 September, 2025; originally announced September 2025.

Comments: The first two authors contributed equally

Journal ref: NeurIPS 2025 Spotlight

Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysis

Authors: Henrique Correia da Fonseca, António Fernandes, Zhao Song, Theodor Cimpeanu, Nataliya Balabanova, Adeela Bashir, Paolo Bova, Alessio Buscemi, Alessandro Di Stefano, Manh Hong Duong, Elias Fernandez Domingos, Ndidi Bianca Ogbo, Simon T. Powers, Daniele Proverbio, Zia Ush Shamszaman, Fernando P. Santos, The Anh Han, Marcus Krellner

Abstract: When developers of artificial intelligence (AI) products need to decide between profit and safety for the users, they likely choose profit. Untrustworthy AI technology must come packaged with tangible negative consequences. Here, we envisage those consequences as the loss of reputation caused by media coverage of their misdeeds, disseminated to the public. We explore whether media coverage has the… ▽ More When developers of artificial intelligence (AI) products need to decide between profit and safety for the users, they likely choose profit. Untrustworthy AI technology must come packaged with tangible negative consequences. Here, we envisage those consequences as the loss of reputation caused by media coverage of their misdeeds, disseminated to the public. We explore whether media coverage has the potential to push AI creators into the production of safe products, enabling widespread adoption of AI technology. We created artificial populations of self-interested creators and users and studied them through the lens of evolutionary game theory. Our results reveal that media is indeed able to foster cooperation between creators and users, but not always. Cooperation does not evolve if the quality of the information provided by the media is not reliable enough, or if the costs of either accessing media or ensuring safety are too high. By shaping public perception and holding developers accountable, media emerges as a powerful soft regulator -- guiding AI safety even in the absence of formal government oversight. △ Less

Submitted 2 September, 2025; originally announced September 2025.

Comments: 10 Pages, 7 Figures, accepted in the ALIFE 2025 Conference

OpenAIs HealthBench in Action: Evaluating an LLM-Based Medical Assistant on Realistic Clinical Queries

Authors: Sandhanakrishnan Ravichandran, Shivesh Kumar, Rogerio Corga Da Silva, Miguel Romano, Reinhard Berkels, Michiel van der Heijden, Olivier Fail, Valentine Emmanuel Gnanapragasam

Abstract: Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stakes clinical scenarios. Traditional evaluations are often limited to multiple-choice questions that fail to capture essential competencies such as contextua… ▽ More Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stakes clinical scenarios. Traditional evaluations are often limited to multiple-choice questions that fail to capture essential competencies such as contextual reasoning, contextual awareness, and uncertainty handling. To address these limitations, we evaluate our agentic RAG-based clinical support assistant, DR. INFO, using HealthBench, a rubric-driven benchmark composed of open-ended, expert-annotated health conversations. On the Hard subset of 1,000 challenging examples, DR. INFO achieves a HealthBench Hard score of 0.68, outperforming leading frontier LLMs including the GPT-5 model family (GPT-5: 0.46, GPT-5.2: 0.42, GPT-5.1: 0.40), Grok 3 (0.23), Gemini 2.5 Pro (0.19), and Claude 3.7 Sonnet (0.02) across all behavioral axes (accuracy, completeness, instruction following, etc.). In a separate 100-sample evaluation against similar agentic RAG assistants (OpenEvidence and Pathway.md, now DoxGPT by Doximity), it maintains a performance lead with a HealthBench Hard score of 0.72. These results highlight the strengths of DR. INFO in communication, instruction following, and accuracy, while also revealing areas for improvement in context awareness and response completeness. Overall, the findings underscore the utility of behavior-level, rubric-based evaluation for building reliable and trustworthy AI-enabled clinical support systems. △ Less

Submitted 27 July, 2026; v1 submitted 29 August, 2025; originally announced September 2025.

Comments: 13 pages, two graphs

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.

Real-time deep learning phase imaging flow cytometer reveals blood cell aggregate biomarkers for haematology diagnostics

Authors: Kerem Delikoyun, Qianyu Chen, Liu Wei, Si Ko Myo, Johannes Krell, Martin Schlegel, Win Sen Kuan, John Tshon Yit Soong, Gerhard Schneider, Clarissa Prazeres da Costa, Percy A. Knolle, Laurent Renia, Matthew Edward Cove, Hwee Kuan Lee, Klaus Diepold, Oliver Hayden

Abstract: While analysing rare blood cell aggregates remains challenging in automated haematology, they could markedly advance label-free functional diagnostics. Conventional flow cytometers efficiently perform cell counting with leukocyte differentials but fail to identify aggregates with flagged results, requiring manual reviews. Quantitative phase imaging flow cytometry captures detailed aggregate morpho… ▽ More While analysing rare blood cell aggregates remains challenging in automated haematology, they could markedly advance label-free functional diagnostics. Conventional flow cytometers efficiently perform cell counting with leukocyte differentials but fail to identify aggregates with flagged results, requiring manual reviews. Quantitative phase imaging flow cytometry captures detailed aggregate morphologies, but clinical use is hampered by massive data storage and offline processing. Incorporating hidden biomarkers into routine haematology panels would significantly improve diagnostics without flagged results. We present RT-HAD, an end-to-end deep learning-based image and data processing framework for off-axis digital holographic microscopy (DHM), which combines physics-consistent holographic reconstruction and detection, representing each blood cell in a graph to recognize aggregates. RT-HAD processes >30 GB of image data on-the-fly with turnaround time of <1.5 min and error rate of 8.9% in platelet aggregate detection, which matches acceptable laboratory error rates of haematology biomarkers and solves the big data challenge for point-of-care diagnostics. △ Less

Submitted 11 August, 2025; originally announced August 2025.

MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework

Authors: Nguyen Viet Tuan Kiet, Dao Van Tung, Tran Cong Dao, Huynh Thi Thanh Binh

Abstract: Designing effective algorithmic components remains a fundamental obstacle in tackling NP-hard combinatorial optimization problems (COPs), where solvers often rely on carefully hand-crafted strategies. Despite recent advances in using large language models (LLMs) to synthesize high-quality components, most approaches restrict the search to a single element - commonly a heuristic scoring function -… ▽ More Designing effective algorithmic components remains a fundamental obstacle in tackling NP-hard combinatorial optimization problems (COPs), where solvers often rely on carefully hand-crafted strategies. Despite recent advances in using large language models (LLMs) to synthesize high-quality components, most approaches restrict the search to a single element - commonly a heuristic scoring function - thus missing broader opportunities for innovation. In this paper, we introduce a broader formulation of solver design as a multi-strategy optimization problem, which seeks to jointly improve a set of interdependent components under a unified objective. To address this, we propose Multi-strategy Optimization via Turn-based Interactive Framework (MOTIF) - a novel framework based on Monte Carlo Tree Search that facilitates turn-based optimization between two LLM agents. At each turn, an agent improves one component by leveraging the history of both its own and its opponent's prior updates, promoting both competitive pressure and emergent cooperation. This structured interaction broadens the search landscape and encourages the discovery of diverse, high-performing solutions. Experiments across multiple COP domains show that MOTIF consistently outperforms state-of-the-art methods, highlighting the promise of turn-based, multi-agent prompting for fully automated solver design. △ Less

Submitted 8 December, 2025; v1 submitted 5 August, 2025; originally announced August 2025.

Comments: Accepted as an oral presentation at AAAI 2026. Code available at: https://github.com/HaiAu2501/MOTIF

Using Sentiment Analysis to Investigate Peer Feedback by Native and Non-Native English Speakers

Authors: Brittney Exline, Melanie Duffin, Brittany Harbison, Chrissa da Gomez, David Joyner

Abstract: Graduate-level CS programs in the U.S. increasingly enroll international students, with 60.2 percent of master's degrees in 2023 awarded to non-U.S. students. Many of these students take online courses, where peer feedback is used to engage students and improve pedagogy in a scalable manner. Since these courses are conducted in English, many students study in a language other than their first. Thi… ▽ More Graduate-level CS programs in the U.S. increasingly enroll international students, with 60.2 percent of master's degrees in 2023 awarded to non-U.S. students. Many of these students take online courses, where peer feedback is used to engage students and improve pedagogy in a scalable manner. Since these courses are conducted in English, many students study in a language other than their first. This paper examines how native versus non-native English speaker status affects three metrics of peer feedback experience in online U.S.-based computing courses. Using the Twitter-roBERTa-based model, we analyze the sentiment of peer reviews written by and to a random sample of 500 students. We then relate sentiment scores and peer feedback ratings to students' language background. Results show that native English speakers rate feedback less favorably, while non-native speakers write more positively but receive less positive sentiment in return. When controlling for sex and age, significant interactions emerge, suggesting that language background plays a modest but complex role in shaping peer feedback experiences. △ Less

Submitted 7 August, 2025; v1 submitted 23 July, 2025; originally announced July 2025.

ACM Class: I.2.7; K.3.1