# Research Papers — 2026-04 · bundle page 180 of 233 > Full-text markdown of papers #8951–9000 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/180 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/179.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/181.md) ### Conv-to-Bench: Evaluating Language Models Via User-Assistant Dialogues In Code Tasks Authors: Victor M. dos Santos, Andre C. Castro, Samuel L. de S. Toledo, Bruno M. L. Calura, Lisandra C. de M. Menezes, Raul C. R. Mata, Telma W. de L. Soares, Bryan L. M. de Oliveira Published: 2026-04-07 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2605.26440v1 The rapid advancement of Large Language Models (LLMs) has outpaced the scalability of traditional evaluation benchmarks, which remain heavily dependent on labor-intensive expert curation. We address this bottleneck with Conv-to-Bench, a multi-stage framework that automatically transforms authentic multi-turn user-assistant dialogues into structured, verifiable requirement checklists. By leveraging the "instructional evolution" found in real-world conversational logs, our approach deconstructs fragmented user intent into consolidated instructions and binary evaluation criteria. Applied to the programming domain, Conv-to-Bench produces evaluation sets that demonstrate near-perfect alignment with human-authored standards like BigCodeBench, achieving Spearman correlations of up to $ρ$ = 1.000 with significantly lower computational overhead. Validation of the LLM-as-a-judge framework further confirms its reliability, with the primary evaluator achieving substantial agreement with human-verified ground truth ($κ$ = 0.705). Our comprehensive ablation studies reveal that while multi-turn interactions capture the iterative evolution of user intent, instruction-centric extraction provides a more robust foundation. Ultimately, Conv-to-Bench provides a scalable, cost-effective paradigm for maintaining high-fidelity evaluation standards as user-centric AI applications continue to diversify. --- ### Document Classification Pattern Recognition via Information Fusion: A Systematic Review of Multimodal and Multiview Representation Approaches Authors: Marcin Michał Mirończuk Published: 2026-04-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.23910v2 Information fusion is used widely to improve document classification by the integration of multiple data sources (multimodal) or representations (multiview). However, the field lacks a unified framework, a quantitative synthesis of its effectiveness, and clear guidance for practitioners. This systematic review addresses these gaps by analysing 139 primary studies. It introduces a formal framework to structure the field, presents the results of a qualitative analysis to identify key trends, and performs a random-effects meta-analysis (to our knowledge, the first focused on document classification) to quantify performance gains. Our meta-analysis reveals that multimodal fusion improves accuracy (mean gain of +5.28 percentage points, $p=0.0016$) significantly -- the F1-score effect is directionally positive but statistically non-significant in our primary model. Multiview fusion provides consistent but modest gains for accuracy (+4.67\%), F1-score (+3.08\%), and recall (all $p<0.05$). Critically, our qualitative synthesis uncovers challenges in reproducibility in methodological rigour: only 11.8\% (multimodal) and 23.3\% (multiview) of the studies use statistical tests to validate their findings, which undermines the reliability of many of their results. This review's primary contributions are a unifying framework, the first quantitative evidence base, and data-driven guidelines. This review concludes that successful information fusion depends not on algorithmic complexity, but on the strategic alignment of the fusion method with the task context and a commitment to more rigorous validation. --- ### RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation Authors: Ming Zhu, Juntao Tan, Rithesh Murthy, Jielin Qiu, Liangwei Yang, Wenting Zhao, Silvio Savarese, Shelby Heinecke, Huan Wang Published: 2026-04-07 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.20204v1 LLM-based user simulation is the primary mechanism for end-to-end agent evaluation, yet simulated users are poor proxies for real humans: unconstrained LLM defaults produce a Formalism Ceiling (style match rates of 6-8% against real users), while hand-crafted behavioral directives trigger Directive Amplification, where models hyper-interpret instructions into unnatural behavioral extremes that vary dramatically across simulator models. We present RealUserSim, the first user simulation framework grounded in real behavioral data. From 14,000+ authentic human-LLM conversations (WildChat), we extract 7,275 executable behavioral profiles and use them to ground LLM simulators. A fidelity benchmark (PT3) on 600 conversations across 71+ domains with anti-leakage controls shows that grounded simulation raises match rate from 24.2% to 45.3% across five behavioral dimensions. Agent evaluation on TauBench with 6 simulator models and extensive analysis shows that grounded simulation acts as a realistic stress test, surfacing three failure mechanisms invisible to cooperative simulators (mean -3.2% to -3.5% task success degradation), while Directive Amplification in existing benchmarks produces unrealistic behavior that compromises the validity of agent evaluation. --- ### GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety Authors: Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song Published: 2026-04-07 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.20203v1 As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities from social isolation, limited digital literacy, and cognitive decline, yet existing safety benchmarks largely target general harms and overlook elderly-specific risks. For example, a prompt such as "how to repair a ceiling light alone in the dark" may be benign for most users but poses a serious fall risk for older adults with mobility limitations. We introduce GrandGuard, the first comprehensive framework for assessing and mitigating elderly-specific contextual risks in LLM interactions. We develop a three-level taxonomy with 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains, grounded in real-world incidents, community discussions, and analysis of stakeholder studies. Using this taxonomy, we construct a benchmark of 10,404 labeled prompts and responses, showing that several leading LLMs mishandle elderly-specific contextual risks in over 50% of cases. We mitigate these failures with two safeguards: a fine-tuned Llama-Guard-3 and a policy-enhanced gpt-oss-safeguard-20b, achieving up to 96.2% and 90.9% unsafe-prompt detection accuracy, respectively. GrandGuard lays the groundwork for AI systems that move beyond general safety to support aging populations. --- ### SparseOIT: Improving Order-Independent Transparency 3DGS via Active Set Method Authors: Wentao Yang, Fanzhen Kong, Zejian Kang, Xiangru Huang Published: 2026-04-07 Categories: cs.GR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.13855v1 3D Gaussian Splatting (3DGS) has received tremendous popularity over the past few years due to its photorealistic visual appearance. However, 3DGS uses volumetric rendering that is not suitable for objects with non-lambertian or transparent materials. To remedy this issue, a family of Order-Independent Transparency (OIT) rendering methods propose to remove or modify the depth sorting step in the 3DGS rendering equation. However, the potential of OIT-based method is still underexplored. In this paper, we observe that the OIT modifications to the rendering equation significantly reduce the inter-independence among individual gaussian splats, resulting in very sparse variable dependencies that can be harnessed by specific optimization techniques such as active set method. To this end, we propose SparseOIT, an OIT-based 3DGS reconstruction algorithm that maintains an active set of gaussian splats and enjoys an acceleration ratio that is proportional to the potential sparsity. SparseOIT is designed by jointly considering the OIT rendering equation, the reconstruction algorithm and the geometric regularization. Through extensive experiments, we demonstrate that SparseOIT outperforms existing methods in the OIT-family by a large margin and also achieves comparable performance to the state-of-the-art 3DGS reconstruction methods based on volumetric rendering. Project page: --- ### Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism Authors: Konstantine Arkoudas, Serafim Batzoglou Published: 2026-04-07 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2605.12524v1 We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid contains 15 tasks spanning proof writing, proof checking, proof masking, and proof gap-filling. Tasks are expressed in minimal formal notation, especially NDL, a compact natural-deduction language that fits in short prompts and supports precise, auditable verification. This yields mechanical, reproducible, and fine-grained evaluation rather than judgments by humans or LLMs. ProofGrid covers a calibrated difficulty spectrum, from foundational reasoning tests to structurally rich challenge tasks that no current model solves, while minimizing reliance on domain knowledge, solver delegation, and long-context artifacts. We also develop a comparative framework for reasoning benchmarks and use it to situate ProofGrid relative to existing work in terms of representation, verification guarantees, and reasoning depth. Methodologically, we introduce an instrumented proof-checking pipeline that tolerates minor surface deviations while locating the first substantive reasoning failure, improving measurement resolution and separating proof planning from low-level execution noise. Using this pipeline, we evaluate a broad range of open and proprietary models. Results show rapid progress but substantial remaining limits: frontier models perform well on several foundational tasks, yet difficult tasks, especially those requiring global combinatorial reasoning or low-level proof synthesis, remain far from solved. We also identify epistemic instability, where models generate flawed proofs yet correctly reject those local inferences in isolation, and formalize this with an Epistemic Stability Index. Finally, we complement accuracy with 2PL IRT analyses, Wright maps, and a normalized task-discrimination measure based on Fisher information. --- ### Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models Authors: Sakshi Agarwal, Aishik Konwer, Ankit Parag Shah Published: 2026-04-07 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.02912v1 Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor precise spatial localization of anomalous events. While Vision-Language Models (VLMs) offer rich scene understanding, they struggle with reliable spatial grounding - often producing hallucinated or geometrically invalid bounding boxes when asked to localize objects. We propose VANGUARD (Video Anomaly Understanding through Reasoning and Grounding), a framework that unifies anomaly classification, spatial grounding, and chain-of-thought reasoning within a single VLM. VANGUARD introduces a three-stage curriculum that progressively layers training objectives: (1) classifier warmup on frozen backbone features, (2) LoRA-adapted spatial grounding, and (3) chain-of-thought generation. To overcome the sparse annotation typical of VAD benchmarks, we employ a teacher-student annotation pipeline in which a VLM (Qwen3-VL-4B) generates structured per-subclip reasoning trajectories based on manual annotations available from the UCA Dataset. Further, GroundingDINO provides bounding box supervision. On UCF-Crime, VANGUARD achieves 94% ROC-AUC with 84% F1 while simultaneously producing interpretable chain-of-thought explanations and spatial grounding of anomalous objects - capabilities absent from prior VAD methods. Ablations confirm that staged training outperforms monolithic optimization, and that structured reasoning acts as an implicit regularizer yielding more balanced predictions than classification-only fine-tuning. Zero-shot transfer to XD-Violence and ShanghaiTech demonstrates cross-domain generalization without target-domain adaptation. --- ### Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Models Authors: Robert-Jeron Reifert, Alaa Alameer Ahmad, Hayssam Dahrouj, Aydin Sezgin Published: 2026-04-07 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2605.02911v1 Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts. Such a promising vision is concurrently expected to give rise to the need for scalable mechanisms that can select, combine, and orchestrate such experts based on high-level intent and uncertainty descriptions. In this paper, we propose an agentic artificial intelligence (AI)-based network optimization framework that integrates mixture of experts (MoE) architectures with large language models (LLMs). Under the proposed framework, the employed LLM acts as a semantic gate to reason over operator objectives and dynamically compose suitable optimization agents. The proposed framework is formulated in a model-agnostic manner and bridges human-readable network intents with low-level resource allocation decisions, enabling flexible optimization across heterogeneous objectives and operating conditions. As a representative instantiation, we apply the framework to a joint communication and computing network and design a library of specialized optimization experts covering throughput, fairness, and delay-driven objectives under both regular and robust conditions. Numerical simulations demonstrate that the proposed agentic MoE framework consistently achieves near-optimal performance compared to exhaustive expert combinations while outperforming individual experts across diverse objectives, including delay minimization and throughput maximization. --- ### The Oracle's Fingerprint: Correlated AI Forecasting Errors and the Limits of Bias Transmission Authors: Theodor Spiro Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.00844v1 When large language models (LLMs) are consulted as forecasting tools, the independence of individual errors -- the foundation of collective intelligence -- may collapse. We test three conditions necessary for this "epistemic monoculture" to emerge. In Study 1, we show that GPT-4o, Claude, and Gemini exhibit highly correlated forecasting errors on 568 resolved binary prediction questions (mean pairwise error correlation r = 0.77, p < 0.001; r = 0.78 excluding likely-leaked questions), despite being developed independently by different organizations. In Study 2, we test whether this correlated bias has propagated into human crowd forecasts, using a within-question design that tracks community prediction shifts across the ChatGPT launch boundary (November 2022). We find that community forecasts move in the direction predicted by LLMs (r = 0.20, p = 0.007), but this shift is fully explained by rational updating toward ground truth. In Study 3, we examine whether the category-level pattern of human forecasting errors increasingly resembles the LLM bias fingerprint. We find the opposite: pre-ChatGPT human biases already strongly resembled the LLM pattern (r = 0.87), while post-ChatGPT the resemblance weakened (r = -0.28). Together, these findings reveal an epistemic monoculture that is built but not yet activated: three nominally independent AI systems share the same failure modes, amplifying precisely the biases humans already hold. --- ### Generative-AI and the transformation of workforce. A job postings-driven analysis Authors: Diana Maria Popa, Simona-Vasilica Oprea, Adela Bâra Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.00843v1 This paper investigates how generative-artificial intelligence AI is reshaping job requirements, skill compositions and sectoral dynamics across global labor markets. It examines the evolving frequency and framing of AI-related competencies in job postings, exploring whether generative-AI functions primarily as an augmentative or substitutive force in the workplace. A large-scale, multi-source corpus of over 150,000 English-language job postings 2018-2025 is compiled from twelve open-access datasets and one public API. The analytical framework integrates lexical skill extraction, semantic framing, topic modeling, BERTopic, LDA, KMeans, and time-series forecasting ARIMA. Skill mentions are categorized into five dimensions: AI_Data, Routine, Soft_Meta, Domain_Specific and Leadership, while cross sectoral analyses and correlation matrices quantify interdependencies between competencies. Sentence-transformer embeddings and cosine similarity are used to compute a Framing Index, distinguishing augmentation- versus automation-oriented discourse. Investigating job postings, our research contributes a replicable, data driven methodology for mapping the diffusion of AI related skills across industries and time. Results reveal a sharp post-2021 increase in AI-related skill mentions: prompt engineering, fine-tuning and model validation, accompanied by a decline in routine tasks: data entry and manual coding. Forecasts suggest sustained growth in AI_Data and Soft_Meta skills through 2025, signaling a structural convergence toward hybrid human-AI expertise as a new foundation of employability. --- ### Understanding Emergent Misalignment via Feature Superposition Geometry Authors: Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo Published: 2026-04-07 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.00842v1 Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. To uncover the reason behind this phenomenon, we propose a geometric account based on the geometry of feature superposition. Because features are encoded in overlapping representations, fine-tuning that amplifies a target feature also unintentionally strengthens nearby harmful features in accordance with their similarity. We give a simple gradient-level derivation of this effect and empirically test it in multiple LLMs (Gemma-2 2B/9B/27B, LLaMA-3.1 8B, GPT-OSS 20B). Using sparse autoencoders (SAEs), we identify features tied to misalignment-inducing data and to harmful behaviors, and show that they are geometrically closer to each other than features derived from non-inducing data. This trend generalizes across domains (e.g., health, career, legal advice). Finally, we show that a geometry-aware approach, filtering training samples closest to toxic features, reduces misalignment by 34.5%, substantially outperforming random removal and achieving comparable or slightly lower misalignment than LLM-as-a-judge-based filtering. Our study links emergent misalignment to feature superposition, providing a basis for understanding and mitigating this phenomenon. --- ### LLM Biases Authors: Jinhui Han, Ming Hu, Xilin Zhang Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.26960v1 Transformer-based agentic AI is rapidly being deployed on major platforms to help users shop, watch, and navigate content with less effort. While these systems can deliver impressive performance, a key concern is whether they may be less reliable than they appear. We ask a simple but fundamental question: whether the mechanisms that make transformer-based agents effective can also induce systematic biases or distortions? We study this question through a theoretical analysis of transformer-based generative recommenders, in which the next user interaction is generated sequentially from the user history. Focusing on how the model allocates attention across historical evidence, we identify four bias channels: (i) Positional bias: stronger positional encoding shifts influence toward recent history, improving responsiveness but potentially reducing stability and long-term diversity; (ii) Popularity amplification: small frequency differences in data can be magnified into disproportionate exposure, contributing to Matthew effects and echo chambers; (iii) Latent driver bias: when important drivers of user choices are not directly observed, the model can place overly concentrated weight on a small subset of past events, creating overconfident attributions. (iv) Synthetic data bias: when users increasingly follow AI suggestions and platforms retrain on model-shaped synthetic logs, outputs can concentrate over time, and long-tail alternatives can disappear first. Our analysis highlights mechanism-level reliability risks that may not be visible in offline performance metrics. The four bias channels indicate that large-scale deployment may systematically distort exposure and choice. For managers, the immediate implication is to treat these as operational risk factors and to monitor concentration and drift over time, rather than assuming that performance gains alone guarantee reliability. --- ### CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs Authors: Elham Nasarian, Abhilash Neog, Kwok-Leung Tsui, Niyousha HosseiniChimeh Published: 2026-04-07 Categories: cs.CY, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.26959v1 Integrating large language models (LLMs) into patient-facing healthcare systems offers significant potential to improve access to medical information. However, ensuring clinical safety and factual reliability remains a critical challenge. In practice, AI-generated responses may be conditionally correct yet medically inappropriate, as models often fail to interpret patient context and tend to produce agreeable responses rather than challenge unsafe assumptions. Unlike clinicians, who infer risk from incomplete information, LLMs frequently lack contextual awareness. Moreover, real-world patient interactions are open-ended and underspecified, unlike structured benchmark settings. We present CareGuardAI, a risk-aware safety framework for patient-facing medical question answering that addresses two key failure modes: clinical safety risk and hallucination risk. The framework introduces Clinical Safety Risk Assessment (SRA), inspired by ISO 14971, and Hallucination Risk Assessment (HRA) to evaluate medical risk and factual reliability. At inference time, CareGuardAI employs a multi-stage pipeline consisting of a controller agent, safety-constrained generation, and dual risk evaluation, followed by iterative refinement when necessary. Responses are released only when both SRA and HRA are less than or equal to 2, ensuring clinically acceptable outputs with bounded latency. We evaluate CareGuardAI on PatientSafeBench, MedSafetyBench, and MedHallu, covering both safety and hallucination detection. Across these benchmarks, the framework consistently outperforms strong baseline models, including GPT-4o-mini, demonstrating the importance of context-aware, risk-based, inference-time safety mechanisms for reliable deployment in healthcare. --- ### Designing Ethical Learning for Agentic AI: Toegye Yi Hwang's Ethical Emotion Regulation Framework Authors: Ji Yeon Kim Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.26958v1 Agentic AI systems capable of autonomous goal setting and proactive intervention introduce new challenges for regulating moral-emotional processes in learning environments. Existing frameworks typically treat emotion as reactive feedback or engagement optimization, overlooking the need for normative regulation across autonomous decision cycles.This paper proposes an ethical emotion regulation framework for agentic AI learning design inspired by Toegye Yi Hwang's moral-emotional philosophy. The Ethical Emotion Feedback System (EEFS) is reconstructed as a five-stage architecture aligned with agentic cycles, articulating stage-specific design principles and scenario classifications.An EEFS Evaluation Instrument is introduced to enable systematic assessment of moral-emotional alignment in agentic AI systems. --- ### LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models Authors: Ashutosh Raj Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.25934v1 The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, principally hallucination, fails to adequately characterize. This paper introduces LLM Psychosis as a structured theoretical framework for pathological breakdowns in model cognition that exhibit functional resemblance to clinically recognized psychotic disorders. Five hallmark features define the framework: reality-boundary dissolution, persistence of injected false beliefs, logical incoherence under impossible constraints, self-model instability, and epistemic overconfidence. We argue these constitute a qualitatively distinct failure mode rather than a mere intensification of ordinary factual error. To operationalize the framework, we propose the LLM Cognitive Integrity Scale (LCIS), a five-axis diagnostic instrument organized around Environmental Reality Interface (ERI), Premise Arbitration Integrity (PAI), Logical Constraint Recognition (LCR), Self-Model Integrity (SMI), and Epistemic Calibration Integrity (ECI). We administer a targeted adversarial probe battery to ChatGPT 5 (GPT-5, OpenAI) and report empirical findings for each axis, documenting both intact-integrity baseline responses and the specific psychosis-like failure signatures elicited under adversarial escalation. Results support a three-tier severity taxonomy: Type I (Confabulatory), Type II (Delusional), and Type III (Dissociative). We further formalize the delusional gradient, a self-reinforcing dynamic in which correction pressure intensifies rather than resolves psychosis-like states, as the most consequential failure mode for deployed systems. Implications for safety evaluation, high-stakes deployment screening, and mechanistic interpretability research are discussed. --- ### UGAF-ITS: A Standards Harmonization Framework and Validation Tool for Multi-Framework AI Governance in Distributed Intelligent Transportation Systems Authors: Talal Ashraf Butt, Muhammad Iqbal, Razi Iqbal Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.22789v2 Organizations deploying AI-enabled Intelligent Transportation Systems face fragmented governance: ISO/IEC~42001 demands a certifiable management system, the EU AI Act imposes binding high-risk obligations from August~2026, and the NIST AI Risk Management Framework structures voluntary practice. This paper introduces UGAF-ITS, a standards harmonization framework that consolidates 154 source obligations from the three instruments into 12 unified controls across eight governance domains through a reproducible five-phase crosswalk methodology. A three-tier operating model allocates each control to the vehicle, edge, or cloud tier where enforcement and defensible evidence production are feasible. An evidence backbone of 20 versioned artifacts supports a single audit package across all three frameworks without duplicating content. We evaluate UGAF-ITS through an open-source governance engine applied to four architecturally distinct ITS deployment scenarios. The engine encodes the complete crosswalk catalog and executes eight compliance computations. Three-tier deployments achieve 91.7\% average scoped framework coverage with 45.9\% evidence reduction, complete bidirectional traceability, and 80\% of artifacts serving all three frameworks simultaneously. Partial deployments contract predictably, with reduction holding between 25\% and 50\% across archetypes. The siloed baseline is enumerated document by document and computed by the tool at run time. These results establish structural properties of the harmonized catalog under architectural variation. They do not establish operational compliance readiness, which external assessment with practitioners has yet to test. The tool, scenarios, and all reported results are publicly available for independent replication. --- ### UGAF-ITS: A Standards Harmonization Framework and Validation Tool for Multi-Framework AI Governance in Distributed Intelligent Transportation Systems Authors: Talal Ashraf Butt, Muhammad Iqbal, Razi Iqbal Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.22789v1 Organizations deploying AI-enabled Intelligent Transportation Systems face fragmented governance: ISO/IEC 42001 demands a certifiable management system, the EU AI Act imposes binding high-risk obligations from August 2026, and the NIST AI Risk Management Framework structures voluntary practice. Each instrument is internally coherent, yet they drive different control vocabularies, evidence expectations, and audit rhythms. In distributed ITS deployments where vehicle manufacturers, roadside integrators, and cloud operators each hold partial evidence and partial accountability, this fragmentation multiplies compliance effort and obscures incident traceability. This paper introduces UGAF-ITS, a standards harmonization framework that consolidates 154 source obligations from the three instruments into 12 unified controls across eight governance domains through a reproducible five-phase crosswalk methodology. A three-tier operating model allocates each control to the vehicle, edge, or cloud tier where enforcement and defensible evidence production are feasible. An evidence backbone of 20 versioned artifacts supports a single audit package across all three frameworks without duplicating content. We validate UGAF-ITS through an open-source governance engine evaluated across four architecturally distinct ITS deployment scenarios. The engine encodes the complete crosswalk catalog and executes eight compliance computations. Three-tier deployments achieve 91.7% average framework coverage with 45.9% evidence reduction, complete bidirectional traceability, and 80% of artifacts serving all three frameworks simultaneously. Partial deployments degrade gracefully: coverage and reduction scale with architectural complexity. The tool, scenarios, and all reported results are publicly available for independent replication. --- ### The Biggest Risk of Embodied AI is Governance Lag Authors: Shaoshan Liu Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.21938v2 Embodied AI is widely discussed as a job-displacement problem. The deeper risk, however, is governance lag: the time and capability gap between a measurable change in technology deployment and an institutional response able to address its consequences. Building on the established pacing problem and the Collingridge dilemma, this article argues that embodied AI intensifies that gap through scalable models and platforms, task-level reorganization, and the separation of upstream technological control from downstream social impact. We distinguish three mutually reinforcing forms of lag, observational, institutional, and distributive, and propose a compliance architecture based on deployment visibility, stack-level accountability, trigger-based adjustment, and automatic distributional response. The central policy challenge is not automation alone, but whether governance systems can become observable, responsive, and adaptive before disruption becomes entrenched. --- ### The Biggest Risk of Embodied AI is Governance Lag Authors: Shaoshan Liu Published: 2026-04-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.21938v1 Embodied AI is widely discussed as a job-displacement problem. The deeper risk, however, is governance lag: the inability of public institutions to keep pace with how fast the technology spreads through the physical economy. As reusable robotic platforms are combined with increasingly general AI models, embodied AI may scale across manufacturing, logistics, care, and infrastructure faster than governance systems can observe, interpret, and respond. We argue that this lag appears in three connected forms: observational, institutional, and distributive. The central policy challenge, therefore, is not automation alone, but whether governance and compliance systems can adapt before disruption becomes entrenched. --- ### Handbook of Rough Set Extensions and Uncertainty Models Authors: Takaaki Fujita, Florentin Smarandache Published: 2026-04-07 Categories: cs.AI, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2604.19794v1 Rough set theory models uncertainty by approximating target concepts through lower and upper sets induced by indiscernibility, or more generally, by granulation relations in data tables. This perspective captures vagueness caused by limited observational resolution and supports set-theoretic reasoning about what can be determined with certainty and what remains only possible. This book is written as a map of models. Rather than developing a single algorithmic pipeline in depth, it provides a systematic survey of the main rough set paradigms and their extension routes. More specifically, representative variants are organized according to (i) the underlying granulation mechanism, such as equivalence-based, tolerance-based, covering-based, neighborhood-based, and probabilistic approximations, and (ii) the uncertainty semantics attached to data and relations, such as crisp, fuzzy, intuitionistic fuzzy, neutrosophic, and plithogenic settings. The book also explains how each choice changes the form of approximations and the interpretation of boundary regions. Throughout the book, small illustrative examples are used to clarify modeling intent and typical use cases in classification and decision support. Finally, an important clarification of scope should be noted. Since the main purpose of this book is to provide a map of models, the Abstract and Introduction should not lead readers to expect that feature reduction and rule induction are primary objectives. Although these topics are central in the rough set literature, they are treated here mainly as motivating applications and as entry points to the broader research landscape. The principal aim of the book is to survey and position rough set models and their extensions in a systematic and coherent manner. --- ### SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation Authors: Hao Liu, Dongyu Li Published: 2026-04-07 Categories: cs.AI, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.19793v1 LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool descriptions. As a result, semantic-only methods can produce negative Kendall-$τ$ in structured workflow domains. We introduce SkillGraph, a directed weighted execution-transition graph mined from 49,831 successful LLM agent trajectories, which encodes workflow-precedence regularities as a reusable graph foundation prior. Building on this graph foundation prior, we propose a two-stage decoupled framework: GS-Hybrid retrieval for candidate selection and a learned pairwise reranker for ordering. On ToolBench (9,965 test instances; ~16,000 tools), the method reaches Set-F1 = 0.271 and Kendall-$τ$ = 0.096; on API-Bank, Kendall-$τ$ improves from -0.433 to +0.613. Under identical Stage-1 inputs, the learned reranker also outperforms LLaMA-3.1-8B Stage-2 rerankers. --- ### Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo Authors: Jelena Markovic-Voronov, Wenhui Zhu, Bo Long, Zhipeng Wang, Suyash Gupta, Kayhan Behdin, Bee-Chung Chen, Deepak Agarwal Published: 2026-04-07 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.16453v1 We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-level likelihood rather than sequence-level quality. Our method defines a reward-augmented target distribution over complete sequences by combining model transition probabilities with prefix-dependent reward potentials. Importantly, the approach is training-free: it leaves model weights unchanged and instead modifies the inference distribution via reward potentials, with all gains arising purely from inference-time sampling. To sample from this distribution, we develop Sequential Monte Carlo algorithms, including a computationally efficient prefix-only variant and a lookahead variant whose intermediate targets match the exact marginals of the full sequence distribution. The framework also integrates resample-move updates with Metropolis-Hastings rejuvenation and supports block-wise generation, subsuming common decoding strategies such as temperature sampling and power-tempered objectives. Empirical results across three 7B models show significant gains. On code generation (HumanEval), our method improves base performance by up to 54.9% and surpasses the strongest sampling baselines by 9.1%-15.3%. On mathematical reasoning (MATH500), it achieves gains of up to 8.8%. Notably, it reaches 87.8% on HumanEval and 78.4% on MATH500 with Qwen2.5-7B, consistently outperforming the reinforcement learning method GRPO. --- ### SynopticBench: Evaluating Vision-Language Models on Generating Weather Forecast Discussions of the Future Authors: Timothy B. Higgins, Antonios Mamalakis, Chirag Agarwal Published: 2026-04-07 Categories: cs.CL, cs.CV, cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2604.16451v1 Recent advances in visual-language models (VLMs) have led to significant improvements in a plethora of complex multimodal tasks like image captioning, report generation, and visual perception. However, generating text from meteorological data is highly challenging because the atmosphere is a chaotic system that is rapidly changing at various spatial and temporal scales. Given the complexity of atmospheric phenomena, it is critical to verifiably quantify the effectiveness of existing VLMs on weather forecasting data. In this work, we present SynopticBench, a high-quality dataset consisting of 1,367,041 text samples of Area Forecast Discussions created by the National Weather Service over the continental United States paired to images of 500mb geopotential height, 2 meter temperature, and 850mb wind velocity in weather forecasts. We also present Synoptic Phenomena Alignment and Coverage Evaluation (SPACE), a novel evaluation framework that can be used to effectively estimate the quality of text descriptions of synoptic weather phenomena. Extensive experiments on generating forecast discussions using state-of-the-art VLMs show the sensitivity of existing evaluation metrics in this domain and enable further exploration into synoptic weather and climate text generation. --- ### Evaluating Intersectional Fairness across Clinical Machine Learning Use Cases using Fairlogue and the All of Us Research Program Authors: Nick Souligne, Vignesh Subbian Published: 2026-04-07 Categories: cs.CY, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2604.16450v2 Intersectional biases in healthcare data can produce compound disparities in clinical machine learning models, yet most fairness evaluations assess demographic attributes independently. FairLogue, a toolkit for intersectional fairness auditing, was applied across multiple clinical prediction tasks to evaluate disparities across combined demographic groups. Using the All of Us dataset, two published models were selected for replication and evaluation: (A) prediction of selective serotonin reuptake inhibitor associated bleeding events and (B) two-year stroke risk in patients with atrial fibrillation. Observational fairness metrics were computed across race, gender, and intersectional subgroups, followed by counterfactual analysis to evaluate whether disparities were attributable to group membership. Intersectional evaluation revealed larger disparities than single-axis analyses; however, counterfactual diagnostics indicated that most observed disparities were comparable to those expected under randomized group membership. These results highlight the importance of intersectional fairness auditing and demonstrate how FairLogue provides deeper insight into bias in clinical machine learning systems. --- ### FM-CAC: Carbon-Aware Control for Battery-Buffered Edge AI via Time-Series Foundation Models Authors: Kang Yang, Walid A. Hanafy, Prashant Shenoy, Mani Srivastava Published: 2026-04-07 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2604.16448v1 As edge AI deployments scale to billions of devices running always-on, real-time compound AI pipelines, they represent a massive and largely unmanaged source of energy consumption and carbon emissions. To reduce carbon emissions while maximizing Quality-of-Service (QoS), this paper proposes FM-CAC, a proactive carbon-aware control framework that leverages a battery as an active temporal buffer. By decoupling energy acquisition from energy consumption, FM-CAC can maximize the use of low-carbon energy, substantially reducing carbon emissions. At each control step, FM-CAC jointly optimizes the software pipeline variant, the hardware operating point, and the battery charging and discharging actions. To support this decision process, FM-CAC leverages edge-friendly Time-Series Foundation Models (TSFMs) for zero-shot carbon forecasting and integrates these forecasts into a dynamic programming solver with deferred cost attribution to prevent myopic battery depletion. Results show that FM-CAC reduces carbon emissions by up to 65.6% while maintaining near-maximum inference accuracy. --- ### A High-Accuracy Optical Music Recognition Method Based on Bottleneck Residual Convolutions Authors: Junwen Ma, Huhu Xue, Xingyuan Zhao, and Weicheng Fu Published: 2026-04-07 Categories: cs.CV, cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2604.16446v1 Optical Music Recognition (OMR) aims to convert printed or handwritten music score images into editable symbolic representations. This paper presents an end-to-end OMR framework that combines residual bottleneck convolutions with bidirectional gated recurrent unit (BiGRU)-based sequence modeling. A convolutional neural network with ResNet-v2-style residual bottleneck blocks and multi-scale dilated convolutions is used to extract features that encode both fine-grained symbol details and global staff-line structures. The extracted feature sequences are then fed into a BiGRU network to model temporal dependencies among musical symbols. The model is trained using the Connectionist Temporal Classification loss, enabling end-to-end prediction without explicit alignment annotations. Experimental results on the Camera-PrIMuS and PrIMuS datasets demonstrate the effectiveness of the proposed framework. On Camera-PrIMuS, the proposed method achieves a sequence error rate (SeER) of $7.52\%$ and a symbol error rate (SyER) of $0.45\%$, with pitch, type, and note accuracies of $99.33\%$, $99.60\%$, and $99.28\%$, respectively. The average training time is 1.74~s per epoch, demonstrating high computational efficiency while maintaining strong recognition performance. On PrIMuS, the method achieves a SeER of $8.11\%$ and a SyER of $0.49\%$, with pitch, type, and note accuracies of $99.27\%$, $99.58\%$, and $99.21\%$, respectively. A fine-grained error analysis further confirms the effectiveness of the proposed model. --- ### SAND: The Challenge on Speech Analysis for Neurodegenerative Disease Assessment Authors: Giovanna Sannino, Ivanoe De Falco, Nadia Brancati, Laura Verde, Maria Frucci, Daniel Riccio, Vincenzo Bevilacqua, Antonio Di Marino, Lucia Aruta, Valentina Virginia Iuzzolino, Gianmaria Senerchia, Myriam Spisto et al. Published: 2026-04-07 Categories: eess.AS, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.16445v2 Recent advances in Artificial Intelligence (AI) and the exploration of noninvasive, objective biomarkers, such as speech signals, have encouraged the development of algorithms to support the early diagnosis of neurodegenerative diseases, including Amyotrophic Lateral Sclerosis (ALS). Voice changes in subjects suffering from ALS typically manifest as progressive dysarthria, which is a prominent neurodegenerative symptom because it affects patients as the disease progresses. Since voice signals are complex data, the development and use of advanced AI techniques are fundamental to extracting distinctive patterns from them. Validating AI algorithms for ALS diagnosis and monitoring using voice signals is challenging, particularly due to the lack of annotated reference datasets. In this work, we present the outcome of a collaboration between a multidisciplinary team of clinicians and Machine Learning experts to create both a clinically annotated validation dataset and the "Speech Analysis for Neurodegenerative Diseases" (SAND) challenge based on it. Specifically, by analyzing voice disorders, the SAND challenge provides an opportunity to develop, test, and evaluate AI models for the automatic early identification and prediction of ALS disease progression. --- ### Thermal-GEMs: Generalized Models for Building Thermal Dynamics Authors: Felix Koch, Fabian Raisch, Benjamin Tischler Published: 2026-04-07 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2604.16443v1 Data-driven models for building thermal dynamics are a scalable approach for enabling energy-efficient operation through fault detection & diagnosis or advanced control. To obtain accurate models, measurement data from a target building spanning months to years are required. Transfer Learning (TL) mitigates this challenge by employing pretrained models based on single or multiple source buildings. General multi-source TL models promise to outperform single-source TL, but alternative multi-source modeling architectures remain to be explored, and evaluation on real-world data is missing. Moreover, time series foundation models (TSFM) have emerged as candidates for the best-performing general models. Hence, we conduct a first, comprehensive assessment of general modeling approaches for building thermal dynamics, including multi-source TL and TSFMs. Our assessment includes ablations using four state-of-the-art multi-source TL architectures and evaluations on synthetic as well as real-world data. We demonstrate that multi-source TL models are highly effective in accurately modeling buildings in real-world applications, yielding up to 63% lower forecasting errors compared to single-source TL. Moreover, our results suggest a trade-off between multi-source TL models exclusively pretrained with building data and TSFMs pretrained with a multitude of different time series, revealing that data from 16-32 source buildings must be available over 1 year for pretraining multi-source TL models to consistently outperform TSFMs as evaluated using the mean absolute error. These findings provide practical guidance for selecting modeling strategies based on the number of source buildings available for pretraining multi-source TL models. --- ### The Breakthrough of Sleep: A Contactless Approach for Accurate Sleep Stage Detection Using the Sleepal AI Lamp Authors: Zhuo Diao, Yueting Li, Jianpeng Wang, Shengyu Guan, Xinwei Wang, Wenxiong Cui, Xin Shi, Tong Liu, Kailai Sun, Jingyu Wang, Dian Fan, Thomas Penzel Published: 2026-04-07 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16442v1 Sleep staging is essential for the assessment of sleep quality and the diagnosis of sleep-related disorders. Conventional polysomnography (PSG), while considered the gold standard, is intrusive, labor-intensive, and unsuitable for long-term monitoring. This study evaluates the performance of the Sleepal AI Lamp, a contactless, radar-based consumer-grade sleep tracker, in comparison with gold-standard polysomnography (PSG), using a large-scale dataset comprising 1022 overnight recordings. We extract multi-scale respiratory and motion-related features from radar signals to train a frequency-augmented deep learning model. For the binary sleep-wake classification task, experimental results demonstrated that the model achieved an accuracy of 92.8% alongside a macro-averaged F1 score of 0.895. For four-stage classification (wake, light NREM (N1 + N2), deep NREM (N3), REM), the model achieved an accuracy of 78.5% with a Cohen's kappa coefficient of 0.695 in healthy individuals and maintained a stable accuracy of 77.2% with a kappa of 0.677 in a heterogeneous population including patients with varying severities of obstructive sleep apnea (OSA). These experimental results demonstrate that the sleep staging performance of the contactless Sleepal AI Lamp is in high agreement with expert-labeled PSG sleep stages. Our findings suggest that non-contact radar sensing, combined with advanced temporal modeling, can provide reliable sleep staging performance without requiring physical contact or wearable devices. Owing to its unobtrusive nature, ease of deployment, and robustness to long-term use, the contactless Sleepal AI Lamp shows strong potential for clinical screening, home-based sleep assessment, and continuous longitudinal sleep monitoring in real-world medical and healthcare applications. --- ### iPhoneme: Brain-to-Text Communication for ALS Using ConformerXL Decoding Authors: Yoonmin Cha, Dawit Chun, Sung Park Published: 2026-04-07 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.16441v1 Brain-computer interfaces (BCIs) for speech restoration hold transformative potential for the approximately 173,000--232,500 individuals worldwide with ALS-related dysarthria. Despite recent progress, high-performance speech BCIs have been demonstrated in only 22--31 patients globally, largely due to limitations in neural decoding accuracy and practical input interfaces. We present iPhoneme, a brain-to-text communication system that jointly addresses these challenges through integrated modeling and interaction design. The system combines a deep learning phoneme decoder based on a modified Conformer architecture (ConformerXL, 192.9M parameters) with a gaze-assisted phoneme input interface that mitigates the Midas touch problem in eye-tracking systems. The acoustic model incorporates a temporal prenet with multi-scale dilated convolutions and bidirectional GRU for neural jitter correction, temporal subsampling for CTC stability, and Pre-RMSNorm stabilization across 12 encoder blocks, trained with AdamW and cosine scheduling. On the interaction side, iPhoneme introduces a chorded gaze-plus-silent-speech paradigm that replaces dwell-time selection, enabling more efficient input. We evaluate the system on the T15 dataset (45 sessions, 8,071 trials) of 256-channel intracranial EEG from speech motor cortex regions. A 6-gram phoneme language model trained on 3.1M sequences, combined with WFST beam search (beam=128), achieves 92.14% phoneme accuracy (7.86% PER) and 73.39% word accuracy (26.61% WER), approximately 3% above prior state-of-the-art. The system operates on CPU with 180 ms latency, demonstrating real-time, high-accuracy brain-to-text communication for ALS. --- ### LatentMimic: Terrain-Adaptive Locomotion via Latent Space Imitation Authors: Zhiquan Wang, Yunyu Liu, Dipam Patel, Ayush Kumar, Aniket Bera, Bedrich Benes Published: 2026-04-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.16440v1 Developing natural and diverse locomotion controllers for quadruped robots that can adapt to complex terrains while preserving motion style remains a significant challenge. Existing imitation-based methods face a fundamental optimization trade-off: strict adherence to motion capture (mocap) references penalizes the geometric deviations required for terrain adaptability, whereas terrain-centric policies often compromise stylistic fidelity. We introduce LatentMimic, a novel locomotion learning framework that decouples stylistic fidelity from geometric constraints. By minimizing the marginal latent divergence between the policy's state-action distribution and a learned mocap prior, our approach provides a conditional relaxation of rigid pose-tracking objectives. This formulation preserves gait topology while permitting independent end-effector adaptations for irregular terrains. We further introduce a terrain adaptation module with a dynamic replay buffer to resolve the policy's distribution shifts across different terrains. We validate our method across four locomotion styles and four terrains, demonstrating that LatentMimic enables effective terrain-adaptive locomotion, achieving higher terrain traversal success rates than state-of-the-art motion-tracking methods while maintaining high stylistic fidelity. --- ### The Deployment Gap in AI Media Detection: Platform-Aware and Visually Constrained Adversarial Evaluation Authors: Aishwarya Budhkar, Trishita Dhara, Siddhesh Sheth Published: 2026-04-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09706v1 Recent AI media detectors report near-perfect performance under clean laboratory evaluation, yet their robustness under realistic deployment conditions remains underexplored. In practice, AI-generated images are resized, compressed, re-encoded, and visually modified before being shared on online platforms. We argue that this creates a deployment gap between laboratory robustness and real-world reliability. In this work, we introduce a platform-aware adversarial evaluation framework for AI media detection that explicitly models deployment transforms (e.g., resizing, compression, screenshot-style distortions) and constrains perturbations to visually plausible meme-style bands rather than full-image noise. Under this threat model, detectors achieving AUC $\approx$ 0{.}99 in clean settings experience substantial degradation. Per-image platform-aware attacks reduce AUC to significantly lower levels and achieve high fake-to-real misclassification rates, despite strict visual constraints. We further demonstrate that universal perturbations exist even under localized band constraints, revealing shared vulnerability directions across inputs. Beyond accuracy degradation, we observe pronounced calibration collapse under attack, where detectors become confidently incorrect. Our findings highlight that robustness measured under clean conditions substantially overestimates deployment robustness. We advocate for platform-aware evaluation as a necessary component of future AI media security benchmarks and release our evaluation framework to facilitate standardized robustness assessment. --- ### Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank Authors: Xiangyong Chen, Xiaochuan Lin, Haoran Liu, Xuan Li, Yichen Su, Xiangwei Guo Published: 2026-04-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09704v1 Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vision-language models (VLMs) to assess perceptual quality. However, existing approaches operate at a single granularity, predicting only an overall quality score, while overlooking the multi-dimensional nature of human quality perception, which encompasses attributes such as sharpness, color fidelity, noise level, and compositional aesthetics. In this paper, we propose MG-IQA (Multi-Granularity IQA), a multi-granularity reasoning framework that extends RL2R to jointly assess overall image quality and fine-grained quality attributes within a single inference pass. Our approach introduces three key innovations: (1) an attribute-aware prompting strategy that elicits structured multi-attribute reasoning from VLMs; (2) a multi-dimensional Thurstone reward model that computes attribute-specific fidelity rewards for group relative policy optimization; and (3) a cross-domain alignment mechanism that enables stable joint training across synthetic distortion, authentic distortion, and AI-generated image datasets without perceptual scale re-alignment. Extensive experiments on eight IQA benchmarks demonstrate that MG-IQA consistently outperforms state-of-the-art methods in both overall quality prediction (average SRCC improvement of 2.1\%) and attribute-level assessment, while generating interpretable, human-aligned quality descriptions. --- ### Identity-Aware U-Net: Fine-grained Cell Segmentation via Identity-Aware Representation Learning Authors: Rui Xiao Published: 2026-04-07 Categories: cs.CV, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2604.09702v1 Precise segmentation of objects with highly similar shapes remains a challenging problem in dense prediction, especially in scenarios with ambiguous boundaries, overlapping instances, and weak inter-instance visual differences. While conventional segmentation models are effective at localizing object regions, they often lack the discriminative capacity required to reliably distinguish a target object from morphologically similar distractors. In this work, we study fine-grained object segmentation from an identity-aware perspective and propose Identity-Aware U-Net (IAU-Net), a unified framework that jointly models spatial localization and instance discrimination. Built upon a U-Net-style encoder-decoder architecture, our method augments the segmentation backbone with an auxiliary embedding branch that learns discriminative identity representations from high-level features, while the main branch predicts pixel-accurate masks. To enhance robustness in distinguishing objects with near-identical contours or textures, we further incorporate triplet-based metric learning, which pulls target-consistent embeddings together and separates them from hard negatives with similar morphology. This design enables the model to move beyond category-level segmentation and acquire a stronger capability for precise discrimination among visually similar objects. Experiments on benchmarks including cell segmentation demonstrate promising results, particularly in challenging cases involving similar contours, dense layouts, and ambiguous boundaries. --- ### PASTA: Vision Transformer Patch Aggregation for Weakly Supervised Target and Anomaly Segmentation Authors: Melanie Neubauer, Elmar Rueckert, Christian Rauch Published: 2026-04-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.09701v1 Detecting unseen anomalies in unstructured environments presents a critical challenge for industrial and agricultural applications such as material recycling and weeding. Existing perception systems frequently fail to satisfy the strict operational requirements of these domains, specifically real-time processing, pixel-level segmentation precision, and robust accuracy, due to their reliance on exhaustively annotated datasets. To address these limitations, we propose a weakly supervised pipeline for object segmentation and classification using weak image-level supervision called 'Patch Aggregation for Segmentation of Targets and Anomalies' (PASTA). By comparing an observed scene with a nominal reference, PASTA identifies Target and Anomaly objects through distribution analysis in self-supervised Vision Transformer (ViT) feature spaces. Our pipeline utilizes semantic text-prompts via the Segment Anything Model 3 to guide zero-shot object segmentation. Evaluations on a custom steel scrap recycling dataset and a plant dataset demonstrate a 75.8% training time reduction of our approach to domain-specific baselines. While being domain-agnostic, our method achieves superior Target (up to 88.3% IoU) and Anomaly (up to 63.5% IoU) segmentation performance in the industrial and agricultural domain. --- ### Attention-Guided Flow-Matching for Sparse 3D Geological Generation Authors: Zhixiang Lu, Mengqi Han, Peixin Guo, Tianming Bai, Jionglong Su, Fei Fang, Sifan Song Published: 2026-04-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09700v1 Constructing high-resolution 3D geological models from sparse 1D borehole and 2D surface data is a highly ill-posed inverse problem. Traditional heuristic and implicit modeling methods fundamentally fail to capture non-linear topological discontinuities under extreme sparsity, often yielding unrealistic artifacts. Furthermore, while deep generative architectures like Diffusion Models have revolutionized continuous domains, they suffer from severe representation collapse when conditioned on sparse categorical grids. To bridge this gap, we propose 3D-GeoFlow, the first Attention-Guided Continuous Flow Matching framework tailored for sparse multimodal geological modeling. By reformulating discrete categorical generation as a simulation-free, continuous vector field regression optimized via Mean Squared Error, our model establishes stable, deterministic optimal transport paths. Crucially, we integrate 3D Attention Gates to dynamically propagate localized borehole features across the volumetric latent space, ensuring macroscopic structural coherence. To validate our framework, we curated a large-scale multimodal dataset comprising 2,200 procedurally generated 3D geological cases. Extensive out-of-distribution (OOD) evaluations demonstrate that 3D-GeoFlow achieves a paradigm shift, significantly outperforming heuristic interpolations and standard diffusion baselines. --- ### OpenKedge: Governing Agentic Mutation with Execution-Bound Safety and Evidence Chains Authors: Jun He, Deying Yu Published: 2026-04-07 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08601v1 The rise of autonomous AI agents exposes a fundamental flaw in API-centric architectures: probabilistic systems directly execute state mutations without sufficient context, coordination, or safety guarantees. We introduce OpenKedge, a protocol that redefines mutation as a governed process rather than an immediate consequence of API invocation. OpenKedge requires actors to submit declarative intent proposals, which are evaluated against deterministically derived system state, temporal signals, and policy constraints prior to execution. Approved intents are compiled into execution contracts that strictly bound permitted actions, resource scope, and time, and are enforced via ephemeral, task-oriented identities. This shifts safety from reactive filtering to preventative, execution-bound enforcement. Crucially, OpenKedge introduces an Intent-to-Execution Evidence Chain (IEEC), which cryptographically links intent, context, policy decisions, execution bounds, and outcomes into a unified lineage. This transforms mutation into a verifiable and reconstructable process, enabling deterministic auditability and reasoning about system behavior. We evaluate OpenKedge across multi-agent conflict scenarios and cloud infrastructure mutations. Results show that the protocol deterministically arbitrates competing intents and cages unsafe execution while maintaining high throughput, establishing a principled foundation for safely operating agentic systems at scale. --- ### Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search Authors: Jiahao Zhang, Shaofei Huang, Yaxiong Wang, Zhedong Zheng Published: 2026-04-07 Categories: cs.IR, cs.CV arXiv: https://arxiv.org/abs/2604.08598v2 Text-based person search faces inherent limitations due to data scarcity, driven by stringent privacy constraints and the high cost of manual annotation. To mitigate this, existing methods usually rely on a Pretrain-then-Finetune paradigm, where models are first pretrained on synthetic person-caption data to establish cross-modal alignment, followed by fine-tuning on labeled real-world datasets. However, this paradigm lacks practicality in real-world deployment scenarios, where large-scale annotated target-domain data is typically inaccessible. In this work, we propose a new Pretrain-then-Adapt paradigm that eliminates reliance on extensive target-domain supervision through an offline test-time adaptation manner, enabling dynamic model adaptation using only unlabeled test data with minimal post-train time cost. To mitigate overconfidence with false positives of previous entropy-based test-time adaptation, we propose an Uncertainty-Aware Test-Time Adaptation (UATTA) framework, which introduces a bidirectional retrieval disagreement mechanism to estimate uncertainty, i.e., low uncertainty is assigned when an image-text pair ranks highly in both image-to-text and text-to-image retrieval, indicating high alignment; otherwise, high uncertainty is detected. This indicator drives offline test-time model recalibration without labels, effectively mitigating domain shift. We validate UATTA on four benchmarks, i.e., CUHK-PEDES, ICFG-PEDES, RSTPReid, and PAB, showing consistent improvements across both CLIP-based (one-stage) and XVLM-based (two-stage) frameworks. Ablation studies confirm that UATTA outperforms existing offline test-time adaptation strategies, establishing a new benchmark for label-efficient, deployable person search systems. Our code is available at https://github.com/nkuzjh/UATTA. --- ### STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System Authors: Wenxiao Zhang, Yu Liu, Qiang sun, Yihao Ding, Sirui Li, Yanbing Liu, Jin B. Hong, Wei Liu Published: 2026-04-07 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2604.08597v1 Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce \textbf{STIndex}, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. \textbf{STIndex} integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, \textbf{STIndex} improves spatiotemporal entity extraction F1 by 4.37\% (GPT-4o-mini) and 3.60\% (Qwen3-8B). A live demonstration and open-source code are available at https://stindex.ai4wa.com/dashboard. --- ### NS-RGS: Newton-Schulz based Riemannian gradient method for orthogonal group synchronization Authors: Haiyang Peng, Deren Han, Xin Chen, Meng Huang Published: 2026-04-07 Categories: stat.ML, cs.IT, cs.LG, math.OC arXiv: https://arxiv.org/abs/2604.07372v1 Group synchronization is a fundamental task involving the recovery of group elements from pairwise measurements. For orthogonal group synchronization, the most common approach reformulates the problem as a constrained nonconvex optimization and solves it using projection-based methods, such as the generalized power method. However, these methods rely on exact SVD or QR decompositions in each iteration, which are computationally expensive and become a bottleneck for large-scale problems. In this paper, we propose a Newton-Schulz-based Riemannian Gradient Scheme (NS-RGS) for orthogonal group synchronization that significantly reduces computational cost by replacing the SVD or QR step with the Newton-Schulz iteration. This approach leverages efficient matrix multiplications and aligns perfectly with modern GPU/TPU architectures. By employing a refined leave-one-out analysis, we overcome the challenge arising from statistical dependencies, and establish that NS-RGS with spectral initialization achieves linear convergence to the target solution up to near-optimal statistical noise levels. Experiments on synthetic data and real-world global alignment tasks demonstrate that NS-RGS attains accuracy comparable to state-of-the-art methods such as the generalized power method, while achieving nearly a 2$\times$ speedup. --- ### The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior Authors: Ameen Patel, Felix Lee, Kyle Liang, Joseph Thomas Published: 2026-04-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07369v1 Emotional prompting - the use of specific emotional diction in prompt engineering - has shown increasing promise in improving large language model (LLM) performance, truthfulness, and responsibility. However these studies have been limited to single types of positive emotional stimuli and have not considered varying degrees of emotion intensity in their analyses. In this paper, we explore the effects of four distinct emotions - joy, encouragement, anger, and insecurity - in emotional prompting and evaluate them on accuracy, sycophancy, and toxicity. We develop a prompt-generation pipeline with GPT-4o mini to create a suite of LLM and human-generated prompts with varying intensities across the four emotions. Then, we compile a "Gold Dataset" of prompts where human and model labels align. Our empirical evaluation on LLM behavior suggests that positive emotional stimuli lead to more accurate and less toxic results, but also increase sycophantic behavior. --- ### Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates Authors: Yao Ji, Guanghui Lan Published: 2026-04-07 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2604.06525v2 Achieving optimal rates for stochastic composite convex optimization without prior knowledge of problem parameters remains a central challenge. In the deterministic setting, the auto-conditioned fast gradient method has recently been proposed to attain optimal accelerated rates without line-search procedures or prior knowledge of the Lipschitz smoothness constant, providing a natural prototype for parameter-free acceleration. However, extending this approach to the stochastic setting has proven technically challenging and remains open. Existing parameter-free stochastic methods either fail to achieve accelerated rates or rely on restrictive assumptions, such as bounded domains, bounded gradients, prior knowledge of the iteration horizon, or strictly sub-Gaussian noise. To address these limitations, we propose a stochastic variant of the auto-conditioned fast gradient method, referred to as stochastic AC-FGM. The proposed method is fully adaptive to the Lipschitz constant, the iteration horizon, and the noise level, enabling both adaptive stepsize selection and adaptive mini-batch sizing without line-search procedures. Under standard bounded conditional variance assumptions, we show that stochastic AC-FGM achieves the optimal iteration complexity of $O(1/\sqrt{\varepsilon})$ and the optimal sample complexity of $O(1/\varepsilon^2)$. --- ### Soft-Quantum Algorithms Authors: Basil Kyriacou, Mo Kordzanganeh, Maniraman Periyasamy, Alexey Melnikov Published: 2026-04-07 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.06523v1 Quantum operations on pure states can be fully represented by unitary matrices. Variational quantum circuits, also known as quantum neural networks, embed data and trainable parameters into gate-based operations and optimize the parameters via gradient descent. The high cost of training and low fidelity of current quantum devices, however, restricts much of quantum machine learning to classical simulation. For few-qubit problems with large datasets, training the matrix elements directly, as is done with weight matrices in classical neural networks, can be faster than decomposing data and parameters into gates. We propose a method that trains matrices directly while maintaining unitarity through a single regularization term added to the loss function. A second training step, circuit alignment, then recovers a gate-based architecture from the resulting soft-unitary. On a five-qubit supervised classification task with 1000 datapoints, this two-step process produces a trained variational circuit in under four minutes, compared to over two hours for direct circuit training, while achieving lower binary cross-entropy loss. In a second experiment, soft-unitaries are embedded in a hybrid quantum-classical network for a reinforcement learning cartpole task, where the hybrid agent outperforms a purely classical baseline of comparable size. --- ### Database Querying under Missing Values Governed by Missingness Mechanisms Authors: Leopoldo Bertossi, Farouk Toumani, Maxime Buron Published: 2026-04-07 Categories: cs.DB, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2604.06520v1 We address the problems of giving a semantics to- and doing query answering (QA) on a relational database (RDB) that has missing values (MVs). The causes for the latter are governed by a Missingness Mechanism that is modelled as a Bayesian Network, which represents a Missingness Graph (MG) and involves the DB attributes. Our approach considerable departs from the treatment of RDBs with NULL (values). The MG together with the observed DB allow to build a block-independent probabilistic DB, on which basis we propose two QA techniques that jointly capture probabilistic uncertainty and statistical plausibility of the implicit imputation of MVs. We obtain complexity results that characterize the computational feasibility of those approaches. --- ### ADP-FL-MedSeg: Adaptive Differential Privacy for Federated Medical Segmentation Across Diverse Modalities Authors: Puja Saha, Eranga Ukwatta Published: 2026-04-07 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.06518v3 Large volumes of medical data remain underutilized because centralizing distributed data is often infeasible due to strict privacy regulations and institutional constraints. In addition, models trained in centralized settings frequently fail to generalize across clinical sites because of heterogeneity in imaging protocols and continuously evolving data distributions arising from differences in scanners, acquisition parameters, and patient populations. Federated learning offers a promising solution by enabling collaborative model training without sharing raw data. However, incorporating differential privacy into federated learning, while essential for privacy guarantees, often leads to degraded accuracy, unstable convergence, and reduced generalization. In this work, we propose an adaptive differentially private federated learning (ADP-FL) framework for medical image segmentation that dynamically adjusts privacy mechanisms to better balance the privacy-utility trade-off. The proposed approach stabilizes training, significantly improves Dice scores and segmentation boundary quality, and maintains rigorous privacy guarantees. We evaluated ADP-FL across diverse imaging modalities and segmentation tasks, including skin lesion segmentation in dermoscopic images, kidney tumor segmentation in 3D CT scans, and brain tumor segmentation in multi-parametric MRI. Compared with conventional federated learning and standard differentially private federated learning, ADP-FL consistently achieves higher accuracy, improved boundary delineation, faster convergence, and greater training stability, with performance approaching that of non-private federated learning under the same privacy budgets. These results demonstrate the practical viability of ADP-FL for high-performance, privacy-preserving medical image segmentation in real-world federated settings. --- ### Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees Authors: Mohammed Nowaz Rabbani Chowdhury, Kaoutar El Maghraoui, Hsinyu Tsai, Naigang Wang, Geoffrey W. Burr, Liu Liu, Meng Wang Published: 2026-04-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.06515v1 Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the large number of parameters still incurs substantial memory overhead during inference. Post-training quantization has been explored to address this issue. Because uniform quantization suffers from significant accuracy loss at low bit-widths, mixed-precision methods have been recently explored; however, they often require substantial computation for bit-width allocation and overlook the varying sensitivity of model performance to the quantization of different experts. We propose a theoretically grounded expert-wise mixed precision strategy that assigns bit-width to each expert primarily based on their change in routers l2 norm during training. Experts with smaller changes are shown to capture less frequent but critical features, and model performance is more sensitive to the quantization of these experts, thus requiring higher precision. Furthermore, to avoid allocating experts to lower precision that inject high quantization noise, experts with large maximum intra-neuron variance are also allocated higher precision. Experiments on large-scale MoE models, including Switch Transformer and Mixtral, show that our method achieves higher accuracy than existing approaches, while also reducing inference cost and incurring only negligible overhead for bit-width assignment. --- ### Fine-tuning Whisper for Pashto ASR: strategies and scale Authors: Hanif Rahman Published: 2026-04-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.06507v1 Pashto is absent from Whisper's pre-training corpus despite being one of CommonVoice's largest language collections, leaving off-the-shelf models unusable: all Whisper sizes output Arabic, Dari, or Urdu script on Pashto audio, achieving word error rates above 100%. We compare four fine-tuning strategies for whisper-base on CommonVoice Pashto v20: vanilla full fine-tuning, LoRA (rank 64), frozen-encoder (2/6 layers), and multistage Urdu-to-Pashto transfer. We extend vanilla fine-tuning to whisper-small and whisper-large-v3-turbo on CommonVoice Pashto v24 (113 hours). Vanilla fine-tuning achieves WER 21.22% on CV20, outperforming LoRA by 33.36 pp, frozen-encoder by 14.76 pp, and Urdu transfer by 44.56 pp. Frozen-encoder fine-tuning degrades performance on whisper-base (6 encoder layers): layer-function separation does not hold at this depth, and freezing removes a third of trainable capacity. Urdu-to-Pashto transfer fails due to an unverified intermediate checkpoint, phonological mismatch, and insufficient training. On CV24, whisper-small achieves WER 24.89% (2.24 pp over whisper-base at 3.3x parameters); whisper-large-v3-turbo achieves 23.37% (a further 1.52 pp). Diminishing returns indicate whisper-small is the practical optimum at 113 hours. Online augmentation provides 7.25 pp WER benefit over matched training. Error analysis identifies word-final suffix confusion (masculine -ay vs. feminine -a) and retroflex substitutions involving the Pashto-unique consonant /ts/ as dominant failure modes. Fine-tuned checkpoints and evaluation scripts are released on HuggingFace. --- ### MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts Authors: Weiyue Li, Ruizhi Qian, Yi Li, Yongce Li, Yunfan Long, Jiahui Cai, Yan Luo, Mengyu Wang Published: 2026-04-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.06505v1 Large language models (LLMs) are widely explored for reasoning-intensive research tasks, yet resources for testing whether they can infer scientific conclusions from structured biomedical evidence remain limited. We introduce $\textbf{MedConclusion}$, a large-scale dataset of $\textbf{5.7M}$ PubMed structured abstracts for biomedical conclusion generation. Each instance pairs the non-conclusion sections of an abstract with the original author-written conclusion, providing naturally occurring supervision for evidence-to-conclusion reasoning. MedConclusion also includes journal-level metadata such as biomedical category and SJR, enabling subgroup analysis across biomedical domains. As an initial study, we evaluate diverse LLMs under conclusion and summary prompting settings and score outputs with both reference-based metrics and LLM-as-a-judge. We find that conclusion writing is behaviorally distinct from summary writing, strong models remain closely clustered under current automatic metrics, and judge identity can substantially shift absolute scores. MedConclusion provides a reusable data resource for studying scientific evidence-to-conclusion reasoning. Our code and data are available at: https://github.com/Harvard-AI-and-Robotics-Lab/MedConclusion. --- ### VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts Authors: Peigui Qi, Kunsheng Tang, Yanpu Yu, Jialin Wu, Yide Song, Wenbo Zhou, Zhicong Huang, Cheng Hong, Weiming Zhang, Nenghai Yu Published: 2026-04-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.06502v1 Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges, we first propose the Multimodal Aggregated Feature Extraction (MAFE) framework that enables CLIP to handle long text and fuse multimodal information into unified representations. Through empirical analysis of MAFE-extracted features, we discover distinct distributional patterns between benign and malicious prompts. Building upon this finding, we develop VLMShield, a lightweight safety detector that efficiently identifies multimodal malicious attacks as a plug-and-play solution. Extensive experiments demonstrate superior performance across multiple dimensions, including robustness, efficiency, and utility. Through our work, we hope to pave the way for more secure multimodal AI deployment. Code is available at (this https URL)(https://github.com/pgqihere/VLMShield). --- ### Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning Authors: Philipp Hellwig, Willem Zuidema, Claire E. Stevenson, Martha Lewis Published: 2026-04-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.06501v2 Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing artificial intelligence systems capable of robust human-like analogical reasoning has proven difficult. In this work, we train transformers using Meta-Learning for Compositionality (MLC) on an analogical reasoning task (letter-string analogies) and assess their generalization capabilities. We find that letter-string analogies become learnable when guiding the models to attend to the most informative problem elements, induced by including copy tasks in the training data. Furthermore, generalization to new alphabets improves when models are trained with more heterogeneous datasets. For the best training run, our 3-layer encoder-decoder model performs on par with frontier models on our letter-string analogy datasets. The MLC approach also enables some generalization to compositions of trained transformations, but not to completely novel transformations. To understand how the model solves the analogies, we identify an algorithm for one analogy task that approximates the model's computations. We verify this using interpretability analyses and show that head-level attention weights causally affect model output, allowing steering between different analogy tasks. We discuss the implications of our findings for generalization capabilities of larger models and the parallels to human analogical reasoning. ---