Hasil untuk "Art"

C. Stoumpos, C. Malliakas, J. A. Peters et al.

S. Attia, M. Egger, Monika Müller et al.

Rhoda Margesson, Johanna K. Bockman

T. Mitchell

K. V. D. Sande, J. Uijlings, T. Gevers et al.

A. Vedaldi, Varun Gulshan, M. Varma et al.

A. L. Bloomfield

Ananya Mantravadi, Shivali Dalmia, Abhishek Mukherji

Reliable clinical decision support requires medical AI agents capable of safe, multi-step reasoning over structured electronic health records (EHRs). While large language models (LLMs) show promise in healthcare, existing benchmarks inadequately assess performance on action-based tasks involving threshold evaluation, temporal aggregation, and conditional logic. We introduce ART, an Action-based Reasoning clinical Task benchmark for medical AI agents, which mines real-world EHR data to create challenging tasks targeting known reasoning weaknesses. Through analysis of existing benchmarks, we identify three dominant error categories: retrieval failures, aggregation errors, and conditional logic misjudgments. Our four-stage pipeline -- scenario identification, task generation, quality audit, and evaluation -- produces diverse, clinically validated tasks grounded in real patient data. Evaluating GPT-4o-mini and Claude 3.5 Sonnet on 600 tasks shows near-perfect retrieval after prompt refinement, but substantial gaps in aggregation (28--64%) and threshold reasoning (32--38%). By exposing failure modes in action-oriented EHR reasoning, ART advances toward more reliable clinical agents, an essential step for AI systems that reduce cognitive load and administrative burden, supporting workforce capacity in high-demand care settings

Ruochen Li, Ziyi Chang, Junyan Hu et al.

Accurate prediction of real-world pedestrian trajectories is crucial for a wide range of robot-related applications. Recent approaches typically adopt graph-based or transformer-based frameworks to model interactions. Despite their effectiveness, these methods either introduce unnecessary computational overhead or struggle to represent the diverse and time-varying characteristics of human interactions. In this work, we present an Adaptive Relational Transformer (ART), which introduces a Temporal-Aware Relation Graph (TARG) to explicitly capture the evolution of pairwise interactions and an Adaptive Interaction Pruning (AIP) mechanism to reduce redundant computations efficiently. Extensive evaluations on ETH/UCY and NBA benchmarks show that ART delivers state-of-the-art accuracy with high computational efficiency.

E. Gombrich

Guan-Yan Yang, Tzu-Yu Cheng, Ya-Wen Teng et al.

The integration of Large Language Models (LLMs) into computer applications has introduced transformative capabilities but also significant security challenges. Existing safety alignments, which primarily focus on semantic interpretation, leave LLMs vulnerable to attacks that use non-standard data representations. This paper introduces ArtPerception, a novel black-box jailbreak framework that strategically leverages ASCII art to bypass the security measures of state-of-the-art (SOTA) LLMs. Unlike prior methods that rely on iterative, brute-force attacks, ArtPerception introduces a systematic, two-phase methodology. Phase 1 conducts a one-time, model-specific pre-test to empirically determine the optimal parameters for ASCII art recognition. Phase 2 leverages these insights to launch a highly efficient, one-shot malicious jailbreak attack. We propose a Modified Levenshtein Distance (MLD) metric for a more nuanced evaluation of an LLM's recognition capability. Through comprehensive experiments on four SOTA open-source LLMs, we demonstrate superior jailbreak performance. We further validate our framework's real-world relevance by showing its successful transferability to leading commercial models, including GPT-4o, Claude Sonnet 3.7, and DeepSeek-V3, and by conducting a rigorous effectiveness analysis against potential defenses such as LLaMA Guard and Azure's content filters. Our findings underscore that true LLM security requires defending against a multi-modal space of interpretations, even within text-only inputs, and highlight the effectiveness of strategic, reconnaissance-based attacks. Content Warning: This paper includes potentially harmful and offensive model outputs.

Alayt Issak, Uttkarsh Narayan, Ramya Srinivasan et al.

Ethical theories and Generative AI (GenAI) models are dynamic concepts subject to continuous evolution. This paper investigates the visualization of ethics through a subset of GenAI models. We expand on the emerging field of Visual Ethics, using art as a form of critical inquiry and the metaphor of a kaleidoscope to invoke moral imagination. Through formative interviews with 10 ethics experts, we first establish a foundation of ethical theories. Our analysis reveals five families of ethical theories, which we then transform into images using the text-to-image (T2I) GenAI model. The resulting imagery, curated as Kaleidoscope Gallery and evaluated by the same experts, revealed eight themes that highlight how morality, society, and learned associations are central to ethical theories. We discuss implications for critically examining T2I models and present cautions and considerations. This work contributes to examining ethical theories as foundational knowledge that interrogates GenAI models as socio-technical systems.

Alejandro H. Artiles, Hiromu Yakura, Levin Brinkmann et al.

In open-ended domains like art, autonomous agents must generate ideas that are both original and internally coherent, yet current Large Language Models (LLMs) either default to familiar cultural patterns or sacrifice coherence when pushed toward novelty. We address this by introducing the Cultural Alien Sampler (CAS), a concept-selection method that explicitly separates compositional fit from cultural typicality. CAS uses two GPT-2 models fine-tuned on WikiArt concepts: a Concept Coherence Model that scores whether concepts plausibly co-occur within artworks, and a Cultural Context Model that estimates how typical those combinations are within individual artists' bodies of work. CAS targets combinations that are high in coherence and low in typicality, yielding ideas that maintain internal consistency while deviating from learned conventions and embedded cultural context. In a human evaluation (N = 100), our approach outperforms random selection and GPT-4o baselines and achieves performance comparable to human art students in both perceived originality and harmony. Additionally, a quantitative study shows that our method produces more diverse outputs and explores a broader conceptual space than its GPT-4o counterpart, demonstrating that artificial cultural alienness can unlock creative potential in autonomous agents.

Parul Dubey, Pushkar Dubey, Pitshou N. Bokoro

Financial fraud detection is a critical application area within the broader domains of cybersecurity and intelligent financial analytics. With the growing volume and complexity of digital transactions, the traditional rule-based and shallow learning models often fall short in detecting sophisticated fraud patterns. This study addresses the challenge of accurately identifying fraudulent financial activities, especially in highly imbalanced datasets where fraud instances are rare and often masked by legitimate behavior. The existing models also lack interpretability, limiting their utility in regulated financial environments. Experiments were conducted on three benchmark datasets: IEEE-CIS Fraud Detection, European Credit Card Transactions, and PaySim Mobile Money Simulation, each representing diverse transaction behaviors and data distributions. The proposed methodology integrates a transformer-based encoder, multi-teacher knowledge distillation, and a symbolic belief–desire–intention (BDI) reasoning layer to combine deep feature extraction with interpretable decision making. The novelty of this work lies in the incorporation of cognitive symbolic reasoning into a high-performance learning architecture for fraud detection. The performance was assessed using key metrics, including the F1-score, AUC, precision, recall, inference time, and model size. Results show that the proposed transformer–BDI model outperformed traditional and state-of-the-art baselines across all datasets, achieving improved fraud detection accuracy and interpretability while remaining computationally efficient for real-time deployment.

E. Gombrich

Eliot W. Robson, Jack Spalding-Jamieson, Da Wei Zheng

We show the following problems are in $\textsf{P}$: 1. The contiguous art gallery problem -- a variation of the art gallery problem where each guard can protect a contiguous interval along the boundary of a simple polygon. This was posed at the open problem session at CCCG '24 by Thomas C. Shermer. 2. The polygon separation problem for line segments -- For two sets of line segments $S_1$ and $S_2$, find a minimum-vertex convex polygon $P$ that completely contains $S_1$ and does not contain or cross any segment of $S_2$. 3. Minimizing the number of half-plane cuts to carve a 3D polytope. To accomplish this, we study the analytic arc cover problem -- an interval set cover problem over the unit circle with infinitely many implicitly-defined arcs, given by a function.

Chloé Galibert-Laîné

From role playing games to animated GIFs, from reenacted performances to poetic writing, this video essay asks: what is an authentic expression of anger?

Chunmei Zhang, Aoran Zhang, Li Zhang et al.

Learning high-quality representations of users, items, and tags from historical interactive data is crucial for personalized tag recommendation (PTR) systems. Currently, most PTR models are committed to learning representations from first-order interactions without considering the exploitation of high-order interactive relations, which can be beneficial for avoiding sub-optimal learning. Although several PTR models equipped with graph neural networks (GNN) have been proposed to capture higher-order semantic relevance from raw data, they all carry out representation learning in Euclidean space, which can still easily result in sub-optimal learning due to embedding distortion. In order to further improve the quality of representation learning for PTR, the paper proposes a novel PTR model based on a lightweight GNN framework with hyperbolic embedding, namely GHPTR. GHPTR explicitly injects higher-order relevance into entity representation through the message propagation and aggregation mechanism of GNN and leverages hyperbolic embedding to alleviate the embedding distortion problem. Experimental results on real-world datasets have demonstrated the superiority of our model over its Euclidean counterparts and state-of-the-art baselines.

Ghaydaa A. Shehata, Hassan M. Farweez, Anwar M. Ali et al.

Abstract Background Parkinson's disease (PD) is a chronic progressive neurodegenerative disabling disease and involves about 1–3% of the worldwide population over the age of 60. A significant prevalence of psychopathological symptoms has been recorded as most patients with PD developed over their disease course neuropsychiatric symptoms such as depression, anxiety, sleep disorders, psychosis, and cognitive and behavioral abnormalities. These non-motor symptoms, which could appear decades before motor ones, become disturbing symptoms during the later phases of the disease. Hence, the current research aims to study depressive symptoms in Parkinson's disease patients. Thirty-six patients with Parkinson’s disease aged from 40 to 65 years (20 males and 16 females) and 36 age and sex-matched controls (19 males and 17 females) were included in the study. Unified Parkinson’s Disease Rating Scale (UPDRS), Hoehn and Yahr scale, Schwab and England’s scale, Mini-Mental State Examination, Cognitive Ability Screening Instrument, and Hamilton Depression Rating Scale were applied to assess depression in both groups. Results Patients were 20 males and 16 females (mean age 52.44 ± 7.45), mean duration of Parkinsonism was 3.88 years. The mean value for Hoehn and Yahr scale was 1.97 ± 1.42, for UPDRS T was 42.41 ± 20.91 and Schwab England's scale was 74.77 ± 17.78. Concerning cognition, MMSE was significantly lower among patients 25.33 ± 3.63, than in the control group and CAS total was significantly lower in patients (16 ± 71.35) than in the control group 9.81 ± 84.62. Conclusion Depressive symptoms are widespread in Parkinson's disease. Depression should be strictly determined and addressed, particularly in patients with more advanced cognitive impairment who are at a higher risk of developing or worsening depression.

Wassily Kandinsky