arXiv:2511.03367v1 Announce Type: cross 
Abstract: Recent advances in large-scale vision and language models have led to significant progress in zero-shot learning tasks. Methods such as CoOp and CoCoOp have shown that replacing handcrafted prompts with learnable vectors, known as prompt learning, can result in improved performance. However, these models often struggle to generalize to entirely unseen categories. While traditional zero-shot learning techniques benefit from various data augmentation strategies, prompt learning has primarily focused on text-based modifications, leaving the potential of image-based augmentation largely unexplored. In this work, we explore how image-level augmentations, particularly those that introduce attribute-specific variations, can support and enhance prompt learning. Our analysis examines the interaction between these augmentations and soft prompt frameworks, revealing their potential to improve generalization. We also identify a limitation in existing methods, such as CoCoOp, which do not provide explicit guidance for learning prompts that focus on semantically meaningful visual features. To address this, we propose Adding Attributes to Prompt Learning, AAPL, a novel method that introduces adversarial token embeddings to decouple superficial visual variations introduced by augmentation from class-relevant semantic representations. This decoupling enables the learned prompts to concentrate on visually discriminative features that align with the target categories. We conduct comprehensive experiments on eleven benchmark datasets, and AAPL consistently outperforms existing methods across few-shot, zero-shot, cross-dataset, and domain generalization settings. Our source code is publicly available at: https://github.com/Gahyeonkim09/AAPL

تسلط الأبحاث الحديثة الضوء على التقدم في نماذج الرؤية واللغة، وخاصة في مهام التعلم بدون عينة. لقد حسنت تقنيات مثل CoOp و CoCoOp الأداء من خلال استخدام مطالبات قابلة للتعلم بدلاً من الثابتة. ومع ذلك، لا تزال هذه النماذج تواجه تحديات في التعميم على فئات جديدة تمامًا. هذه الدراسة مهمة لأنها تتناول قيود الأساليب الحالية وتستكشف كيفية فصل تحيز الزيادة، مما قد يؤدي إلى أنظمة ذكاء اصطناعي أكثر قوة يمكنها فهم وتفسير البيانات غير المرئية بشكل أفضل.

Investigaciones recientes destacan los avances en modelos de visión y lenguaje, especialmente en tareas de aprendizaje sin muestras. Técnicas como CoOp y CoCoOp han mejorado el rendimiento al utilizar indicaciones aprendibles en lugar de fijas. Sin embargo, estos modelos aún enfrentan desafíos para generalizar a nuevas categorías. Este estudio es importante porque aborda las limitaciones de los métodos actuales y explora cómo desacoplar el sesgo de aumento, lo que podría llevar a sistemas de IA más robustos que puedan comprender e interpretar mejor datos no vistos.

Des recherches récentes mettent en lumière les avancées des modèles vision-langage, en particulier dans les tâches d'apprentissage sans échantillon. Des techniques comme CoOp et CoCoOp ont amélioré les performances en utilisant des invites apprenables au lieu de fixes. Cependant, ces modèles rencontrent encore des difficultés à se généraliser à de nouvelles catégories. Cette étude est importante car elle aborde les limites des méthodes actuelles et explore comment découpler le biais d'augmentation, ce qui pourrait conduire à des systèmes d'IA plus robustes capables de mieux comprendre et interpréter des données inédites.

Recent research highlights the advancements in vision-language models, particularly in zero-shot learning tasks. Techniques like CoOp and CoCoOp have improved performance by using learnable prompts instead of fixed ones. However, these models still face challenges in generalizing to new categories. This study is important as it addresses the limitations of current methods and explores how to decouple augmentation bias, potentially leading to more robust AI systems that can better understand and interpret unseen data.

Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models

arXiv:2601.06204v2 Announce Type: replace 
Abstract: Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture low-level deviations without contextual reasoning, object detectors provide speed but limited semantics, and large vision-language systems deliver interpretability at prohibitive computational cost. This work introduces a cascading multi-agent framework that unifies these complementary paradigms into a coherent and interpretable architecture. Early modules perform reconstruction-gated filtering and object-level assessment, while higher-level reasoning agents are selectively invoked to interpret semantically ambiguous events. The system employs adaptive escalation thresholds and a publish-subscribe communication backbone, enabling asynchronous coordination and scalable deployment across heterogeneous hardware. Extensive evaluation on large-scale monitoring data demonstrates that the proposed cascade achieves a threefold reduction in latency compared to direct vision-language inference, while maintaining high perceptual fidelity (PSNR = 38.3 dB, SSIM = 0.965) and consistent semantic labeling. The framework advances beyond conventional detection pipelines by combining early-exit efficiency, adaptive multi-agent reasoning, and explainable anomaly attribution, establishing a reproducible and energy-efficient foundation for scalable intelligent visual monitoring.

تم تقديم إطار عمل جديد للكشف عن الشذوذ متعدد الوكلاء في أنظمة المراقبة، باستخدام نماذج الرؤية-اللغة وتصنيف قائم على التضمين لتحسين الأداء في الوقت الحقيقي وقابلية التفسير الدلالي. تتكامل هذه الطريقة مع منهجيات مختلفة، بما في ذلك التصفية المعتمدة على إعادة البناء والتقييم على مستوى الكائن، لمعالجة تعقيدات الكشف عن الشذوذ في البيئات البصرية الديناميكية.

Se ha introducido un nuevo marco para la detección de anomalías en cascada mediante múltiples agentes en sistemas de vigilancia, utilizando modelos de visión-lenguaje y clasificación basada en embeddings para mejorar el rendimiento en tiempo real y la interpretabilidad semántica. Este enfoque integra diversas metodologías, incluyendo filtrado basado en reconstrucción y evaluaciones a nivel de objeto, para abordar las complejidades de la detección de anomalías en entornos visuales dinámicos.

Un nouveau cadre pour la détection d'anomalies en cascade à plusieurs agents dans les systèmes de surveillance a été introduit, utilisant des modèles de vision-langage et une classification basée sur l'embedding pour améliorer la performance en temps réel et l'interprétabilité sémantique. Cette approche intègre diverses méthodologies, y compris le filtrage basé sur la reconstruction et les évaluations au niveau des objets, pour répondre aux complexités de la détection d'anomalies dans des environnements visuels dynamiques.

A new framework for cascading multi-agent anomaly detection in surveillance systems has been introduced, utilizing vision-language models and embedding-based classification to enhance real-time performance and semantic interpretability. This approach integrates various methodologies, including reconstruction-gated filtering and object-level assessments, to address the complexities of detecting anomalies in dynamic visual environments.

Cascading multi-agent anomaly detection in surveillance systems via vision-language models and embedding-based classification

arXiv:2508.13680v3 Announce Type: replace-cross 
Abstract: We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) interpret and reason over visual and textual information beyond English. VMMU consists of 2.5k multimodal questions across 7 tasks, covering a diverse range of problem contexts, including STEM problem solving, data interpretation, rule-governed visual reasoning, and abstract visual reasoning. All questions require genuine multimodal integration, rather than reliance on text-only cues or OCR-based shortcuts. We evaluate a diverse set of state-of-the-art proprietary and open-source VLMs on VMMU. Despite strong Vietnamese OCR performance, proprietary models achieve only 66% mean accuracy. Further analysis shows that the primary source of failure is not OCR, but instead multimodal grounding and reasoning over text and visual evidence. Code and data are available at https://vmmu.github.io.

تم تقديم VMMU، وهو معيار فيتنامي لفهم وتقييم المهام المتعددة متعددة الوسائط، بهدف تقييم قدرات نماذج اللغة والرؤية (VLM) في تفسير واستنتاج المعلومات المرئية والنصية باللغة الفيتنامية. يتضمن هذا المعيار 2.5 ألف سؤال متعدد الوسائط عبر سبع مهام متنوعة، مع التركيز على التكامل الحقيقي متعدد الوسائط بدلاً من الاعتماد على الإشارات النصية فقط.

La introducción de VMMU, un referente vietnamita para la evaluación de la comprensión y el razonamiento multimodal, tiene como objetivo evaluar las capacidades de los modelos de lenguaje y visión (VLM) para interpretar y razonar sobre información visual y textual en vietnamita. Este referente incluye 2.5k preguntas multimodales en siete tareas diversas, enfatizando la integración multimodal genuina en lugar de depender únicamente de pistas textuales.

L'introduction de VMMU, une référence vietnamienne pour l'évaluation de la compréhension et du raisonnement multimodal, vise à évaluer les capacités des modèles de langage et de vision (VLM) à interpréter et raisonner sur des informations visuelles et textuelles en vietnamien. Cette référence comprend 2,5k questions multimodales réparties sur sept tâches diverses, mettant l'accent sur une véritable intégration multimodale plutôt que sur des indices uniquement textuels.

The introduction of VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark, aims to assess the capabilities of vision-language models (VLMs) in interpreting and reasoning over visual and textual information in Vietnamese. This benchmark includes 2.5k multimodal questions across seven diverse tasks, emphasizing genuine multimodal integration rather than text-only cues.

VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark

One More Thing in AI – Your Shortcut to AI Mastery

Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Chattermate

Scop.ai

The Visualizer

Kansei

Ready to build your own newsroom?