arXiv:2511.18594v1 Announce Type: cross 
Abstract: Integrated sensing and communication and millimeter wave (mmWave) have emerged as pivotal technologies for 6G networks. However, the narrow nature of mmWave beams requires precise alignments that typically necessitate large training overhead. This overhead can be reduced by incorporating the position information with beam adjustments. This letter proposes a lightweight autorencoder (LAE) model that addresses the position-assisted beam prediction problem while significantly reducing computational complexity compared to the conventional baseline method, i.e., deep fully connected neural network. The proposed LAE is designed as a three-layer undercomplete network to exploit its dimensionality reduction capabilities and thereby mitigate the computational requirements of the trained model. Simulation results show that the proposed model achieves a similar beam prediction accuracy to the baseline with an 83% complexity reduction.

تم اقتراح نموذج للترميز التلقائي الخفيف (LAE) لتحسين توقع الشعاع المدعوم بالموقع في أنظمة الاتصالات والاستشعار المتكاملة (ISAC) بترددات المليمتر (mmWave). يقلل هذا النموذج بشكل كبير من التعقيد الحسابي مع الحفاظ على دقة مشابهة لتلك التي توفرها الشبكات العصبية المتصلة بالكامل التقليدية، محققًا تقليلًا بنسبة 83% في التعقيد.

Se ha propuesto un modelo de autoencoder ligero (LAE) para mejorar la predicción de haz asistida por posición en sistemas de comunicación y detección integrados (ISAC) de ondas milimétricas (mmWave). Este modelo reduce significativamente la complejidad computacional mientras mantiene una precisión similar a la de las redes neuronales totalmente conectadas tradicionales, logrando una reducción del 83 % en la complejidad.

Un modèle d'autoencodeur léger (LAE) a été proposé pour améliorer la prédiction de faisceau assistée par position dans les systèmes de communication et de détection intégrés (ISAC) à ondes millimétriques (mmWave). Ce modèle réduit considérablement la complexité computationnelle tout en maintenant une précision similaire à celle des réseaux neuronaux entièrement connectés traditionnels, atteignant une réduction de 83 % de la complexité.

A lightweight autoencoder (LAE) model has been proposed to enhance position-assisted beam prediction in millimeter wave (mmWave) integrated sensing and communication (ISAC) systems. This model significantly reduces computational complexity while maintaining similar accuracy to traditional deep fully connected neural networks, achieving an 83% reduction in complexity.

Autoencoder for Position-Assisted Beam Prediction in mmWave ISAC Systems

arXiv:2512.03248v1 Announce Type: cross 
Abstract: Recent advances in AI call for a paradigm shift from bit-centric communication to goal- and semantics-oriented architectures, paving the way for AI-native 6G networks. In this context, we address a key open challenge: enabling heterogeneous AI agents to exchange compressed latent-space representations while mitigating semantic noise and preserving task-relevant meaning. We cast this challenge as learning both the communication topology and the alignment maps that govern information exchange among agents, yielding a learned network sheaf equipped with orthogonal maps. This learning process is further supported by a semantic denoising end compression module that constructs a shared global semantic space and derives sparse, structured representations of each agent's latent space. This corresponds to a nonconvex dictionary learning problem solved iteratively with closed-form updates. Experiments with mutiple AI agents pre-trained on real image data show that the semantic denoising and compression facilitates AI agents alignment and the extraction of semantic clusters, while preserving high accuracy in downstream task. The resulting communication network provides new insights about semantic heterogeneity across agents, highlighting the interpretability of our methodology.

أدت التطورات الأخيرة في الذكاء الاصطناعي (AI) إلى تحول نحو هياكل الاتصال الموجهة نحو الأهداف والدلالات، خاصة في سياق الشبكات 6G الأصلية للذكاء الاصطناعي. يتضمن ذلك تمكين وكلاء الذكاء الاصطناعي المتنوعين من تبادل تمثيلات الفضاء الكامن المضغوطة مع معالجة الضوضاء الدلالية والحفاظ على المعنى ذي الصلة بالمهمة من خلال حزمة شبكة متعلمة ووحدة ضغط لإزالة الضوضاء الدلالية.

Los avances recientes en inteligencia artificial (IA) han impulsado un cambio hacia arquitecturas de comunicación orientadas a objetivos y semántica, especialmente en el contexto de redes 6G nativas de IA. Esto implica permitir que agentes de IA heterogéneos intercambien representaciones del espacio latente comprimidas, abordando el ruido semántico y preservando el significado relevante para la tarea a través de un haz de red aprendido y un módulo de compresión de desruido semántico.

Les avancées récentes en intelligence artificielle (IA) ont entraîné un changement vers des architectures de communication orientées vers les objectifs et la sémantique, notamment dans le contexte des réseaux 6G natifs à l'IA. Cela implique de permettre à des agents IA hétérogènes d'échanger des représentations de l'espace latent compressées tout en abordant le bruit sémantique et en préservant le sens pertinent pour la tâche grâce à un faisceau de réseau appris et un module de compression de débruitage sémantique.

Recent advancements in artificial intelligence (AI) have prompted a shift towards goal- and semantics-oriented communication architectures, particularly in the context of AI-native 6G networks. This involves enabling heterogeneous AI agents to exchange compressed latent-space representations while addressing semantic noise and preserving task-relevant meaning through a learned network sheaf and a semantic denoising compression module.

Learning Network Sheaves for AI-native Semantic Communication

arXiv:2505.08032v2 Announce Type: replace-cross 
Abstract: Adaptive beam switching is essential for mission-critical military and commercial 6G networks but faces major challenges from high carrier frequencies, user mobility, and frequent blockages. While existing machine learning (ML) solutions often focus on maximizing instantaneous throughput, this can lead to unstable policies with high signaling overhead. This paper presents an online Deep Reinforcement Learning (DRL) framework designed to learn an operationally stable policy. By equipping the DRL agent with an enhanced state representation that includes blockage history, and a stability-centric reward function, we enable it to prioritize long-term link quality over transient gains. Validated in a challenging 100-user scenario using the Sionna library, our agent achieves throughput comparable to a reactive Multi-Armed Bandit (MAB) baseline. Specifically, our proposed framework improves link stability by approximately 43% compared to a vanilla DRL approach, achieving operational reliability competitive with MAB while maintaining high data rates. This work demonstrates that by reframing the optimization goal towards operational stability, DRL can deliver efficient, reliable, and real-time beam management solutions for next-generation mission-critical networks.

تم تقديم إطار جديد للتعلم العميق المعزز (DRL) عبر الإنترنت لتحسين تبديل الشعاع التكيفي في شبكات 6G، حيث يتناول التحديات مثل الترددات الحاملة العالية وتحركات المستخدمين. يركز هذا الإطار على جودة الرابط على المدى الطويل بدلاً من المكاسب المؤقتة، محققًا تحسينًا بنسبة 43% في استقرار الرابط مقارنة بالطرق التقليدية.

Se ha introducido un nuevo marco de Aprendizaje por Refuerzo Profundo (DRL) en línea para mejorar el cambio adaptativo de haz en redes 6G, abordando desafíos como las altas frecuencias portadoras y la movilidad de los usuarios. Este marco prioriza la calidad del enlace a largo plazo sobre las ganancias a corto plazo, logrando una mejora del 43% en la estabilidad del enlace en comparación con los métodos tradicionales.

Un nouveau cadre d'apprentissage par renforcement profond (DRL) en ligne a été introduit pour améliorer le commutateur de faisceau adaptatif dans les réseaux 6G, abordant des défis tels que les hautes fréquences porteuses et la mobilité des utilisateurs. Ce cadre privilégie la qualité de lien à long terme par rapport aux gains à court terme, réalisant une amélioration de 43 % de la stabilité du lien par rapport aux méthodes traditionnelles.

A new online Deep Reinforcement Learning (DRL) framework has been introduced to enhance adaptive beam switching in 6G networks, addressing challenges such as high carrier frequencies and user mobility. This framework prioritizes long-term link quality over short-term gains, achieving a 43% improvement in link stability compared to traditional methods.

Autoencoder for Position-Assisted Beam Prediction in mmWave ISAC Systems

Was this article worth reading? Share it

LucidQuery AI

Attentive AI

LCW