Neural Cellular Automata (NCA) represent a powerful framework for modeling biological self-organization, extending classical rule-based systems with trainable, differentiable (or evolvable) update rules that capture the adaptive self-regulatory dynamics of living matter. By embedding Artificial Neural Networks (ANNs) as local decision-making centers and interaction rules between localized agents, NCA can simulate processes across molecular, cellular, tissue, and system-level scales, offering a multiscale competency architecture perspective on evolution, development, regeneration, aging, morphogenesis, and robotic control. These models not only reproduce biologically inspired target patterns but also generalize to novel conditions, demonstrating robustness to perturbations and the capacity for open-ended adaptation and reasoning. Given their immense success in recent developments, we here review current literature of NCAs that are relevant primarily for biological or bioengineering applications. Moreover, we emphasize that beyond biology, NCAs display robust and generalizing goal-directed dynamics without centralized control, e.g., in controlling or regenerating composite robotic morphologies or even on cutting-edge reasoning tasks such as ARC-AGI-1. In addition, the same principles of iterative state-refinement is reminiscent to modern generative Artificial Intelligence (AI), such as probabilistic diffusion models. Their governing self-regulatory behavior is constraint to fully localized interactions, yet their collective behavior scales into coordinated system-level outcomes. We thus argue that NCAs constitute a unifying computationally lean paradigm that not only bridges fundamental insights from multiscale biology with modern generative AI, but have the potential to design truly bio-inspired collective intelligence capable of hierarchical reasoning and control.

Abstract--Artificial intelligence (AI) is anticipated to emerge as a pivotal enabler for the forthcoming sixth-generation (6G) wireless communication systems. However, current research efforts regarding large AI models for wireless communications primarily focus on fine-tuning pre-trained large language models (LLMs) for specific tasks. This paper investigates the large-scale AI model designed for beamforming optimization to adapt and generalize to diverse tasks defined by system utilities and scales. We propose a novel framework based on bidirectional encoder representations from transformers (BERT), termed BERT4beam. We aim to formulate the beamforming optimization problem as a token-level sequence learning task, perform tokenization of the channel state information, construct the BERT model, and conduct task-specific pre-training and fine-tuning strategies. Based on the framework, we propose two BERT -based approaches for single-task and multi-task beamforming optimization, respectively. Both approaches are generalizable for varying user scales. Moreover, the former can adapt to varying system utilities and antenna configurations by re-configuring the input and output module of the BERT model, while the latter, termed UBERT, can directly generalize to diverse tasks, due to a finer-grained tokenization strategy. Extensive simulation results demonstrate that the two proposed approaches can achieve near-optimal performance and outperform existing AI models across various beamforming optimization tasks, showcasing strong adaptability and generalizability. The upcoming sixth-generation (6G) mobile communication system is expected to achieve ubiquitous and high-quality coverage for a vast number of wireless devices.

This survey offers a comprehensive overview of recent advancements in LiDAR-based autonomous Unmanned Aerial Vehicles (UAVs), covering their design, perception, planning, and control strategies. Over the past decade, LiDAR technology has become a crucial enabler for high-speed, agile, and reliable UAV navigation, especially in GPS-denied environments. The paper begins by examining the evolution of LiDAR sensors, emphasizing their unique advantages such as high accuracy, long-range depth measurements, and robust performance under various lighting conditions, making them particularly well-suited for UAV applications. The integration of LiDAR with UAVs has significantly enhanced their autonomy, enabling complex missions in diverse and challenging environments. Subsequently, we explore essential software components, including perception technologies for state estimation and mapping, as well as trajectory planning and control methodologies, and discuss their adoption in LiDAR-based UAVs. Additionally, we analyze various practical applications of the LiDAR-based UAVs, ranging from industrial operations to supporting different aerial platforms and UAV swarm deployments. The survey concludes by discussing existing challenges and proposing future research directions to advance LiDAR-based UAVs and enhance multi-UAV collaboration. By synthesizing recent developments, this paper aims to provide a valuable resource for researchers and practitioners working to push the boundaries of LiDAR-based UAV systems.

Large Language Models (LLMs) have revolutionized natural language processing with their remarkable capabilities in text generation and reasoning. However, these models face critical challenges when deployed in real-world applications, including hallucination generation, outdated knowledge, and limited domain expertise. Retrieval And Structuring (RAS) Augmented Generation addresses these limitations by integrating dynamic information retrieval with structured knowledge representations. This survey (1) examines retrieval mechanisms including sparse, dense, and hybrid approaches for accessing external knowledge; (2) explore text structuring techniques such as taxonomy construction, hierarchical classification, and information extraction that transform unstructured text into organized representations; and (3) investigate how these structured representations integrate with LLMs through prompt-based methods, reasoning frameworks, and knowledge embedding techniques. It also identifies technical challenges in retrieval efficiency, structure quality, and knowledge integration, while highlighting research opportunities in multimodal retrieval, cross-lingual structures, and interactive systems. This comprehensive overview provides researchers and practitioners with insights into RAS methods, applications, and future directions.

The success and wide adoption of generative AI (GenAI), particularly large language models (LLMs), has attracted the attention of cybercriminals seeking to abuse models, steal sensitive data, or disrupt services. Moreover, providing security to LLM-based systems is a great challenge, as both traditional threats to software applications and threats targeting LLMs and their integration must be mitigated. In this survey, we shed light on security and privacy concerns of such LLM-based systems by performing a systematic review and comprehensive categorization of threats and defensive strategies considering the entire software and LLM life cycles. We analyze real-world scenarios with distinct characteristics of LLM usage, spanning from development to operation. In addition, threats are classified according to their severity level and to which scenarios they pertain, facilitating the identification of the most relevant threats. Recommended defense strategies are systematically categorized and mapped to the corresponding life cycle phase and possible attack strategies they attenuate. This work paves the way for consumers and vendors to understand and efficiently mitigate risks during integration of LLMs in their respective solutions or organizations. It also enables the research community to benefit from the discussion of open challenges and edge cases that may hinder the secure and privacy-preserving adoption of LLM-based systems.

This study investigates the aesthetic experience and educational value of collaborative artmaking with generative artificial intelligence (AI) among young learners and art students. Based on a survey of 112 participants, we examine how human creators renegotiate their roles, how conventional notions of originality are challenged, how the creative process is transformed, and how aesthetic judgment is formed in human-AI co-creation. Empirically, participants generally view AI as a partner that stimulates ideation and expands creative boundaries rather than a passive tool, while simultaneously voicing concerns about stylistic homogenization and the erosion of traditional authorship. Theoretically, we synthesize Dewey's aesthetics of experience, Ihde's postphenomenology, and actor-network theory (ANT) into a single analytical framework to unpack the dynamics between human creators and AI as a non-human actant. Findings indicate (i) a fluid subjectivity in which creators shift across multiple stances (director, dialogic partner, discoverer); (ii) an iterative, dialogic workflow (intent-generate-select-refine) that centers critical interpretation; and (iii) an educational value shift from technical skill training toward higher-order competencies such as critical judgment, cross-modal ideation, and reflexivity. We argue that arts education should cultivate a critical co-creation stance toward technology, guiding learners to collaborate with AI while preserving human distinctiveness in concept formation, judgment, and meaning-making.

Trajectory prediction serves as a critical functionality in autonomous driving, enabling the anticipation of future motion paths for traffic participants such as vehicles and pedestrians, which is essential for driving safety. Although conventional deep learning methods have improved accuracy, they remain hindered by inherent limitations, including lack of interpretability, heavy reliance on large-scale annotated data, and weak generalization in long-tail scenarios. The rise of Large Foundation Models (LFMs) is transforming the research paradigm of trajectory prediction. This survey offers a systematic review of recent advances in LFMs, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) for trajectory prediction. By integrating linguistic and scene semantics, LFMs facilitate interpretable contextual reasoning, significantly enhancing prediction safety and generalization in complex environments. The article highlights three core methodologies: trajectory-language mapping, multimodal fusion, and constraint-based reasoning. It covers prediction tasks for both vehicles and pedestrians, evaluation metrics, and dataset analyses. Key challenges such as computational latency, data scarcity, and real-world robustness are discussed, along with future research directions including low-latency inference, causality-aware modeling, and motion foundation models.

Lithium (Li) batteries have emerged as a dominant energy storage solution due to their exceptional energy density, prolonged cycle life, fast charging capability, and adaptability across diverse applications, including electric vehicles, renewable energy systems, and portable electronics [1, 2, 3]. However, their performance inevitably degrades with time driven by repeated charge and discharge cycles, temperature fluctuations, and ageing effects [4, 5]. This degradation not only reduces battery efficiency and reliability but also poses significant safety risks, particularly in high-demand applications where performance consistency is critical [6], [7]. As a result, accurate estimation of the State of Health (SOH) is essential to ensure the longevity and safe operation of Li batteries. SOH is a key indicator of the remaining capacity and functional integrity of a battery relative to its initial state. It encompasses key variables such as voltage, current, temperature, and other factors that influence battery performance.

This paper reviews the 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real), held in conjunction with ICCV 2025. The workshop aimed to bridge the gap between the theoretical promise of Disentangled Representation Learning (DRL) and its application in realistic scenarios, moving beyond synthetic benchmarks. DRL4Real focused on evaluating DRL methods in practical applications such as controllable generation, exploring advancements in model robustness, interpretability, and generalization. The workshop accepted 9 papers covering a broad range of topics, including the integration of novel inductive biases (e.g., language), the application of diffusion models to DRL, 3D-aware disentanglement, and the expansion of DRL into specialized domains like autonomous driving and EEG analysis. This summary details the workshop's objectives, the themes of the accepted papers, and provides an overview of the methodologies proposed by the authors.

Visual grounding refers to the ability of a model to identify a region within some visual input that matches a textual description. Consequently, a model equipped with visual grounding capabilities can target a wide range of applications in various domains, including referring expression comprehension, answering questions pertinent to fine-grained details in images or videos, caption visual context by explicitly referring to entities, as well as low and high-level control in simulated and real environments. In this survey paper, we review representative works across the key areas of research on modern general-purpose vision language models (VLMs). We first outline the importance of grounding in VLMs, then delineate the core components of the contemporary paradigm for developing grounded models, and examine their practical applications, including benchmarks and evaluation metrics for grounded multimodal generation. We also discuss the multifaceted interrelations among visual grounding, multimodal chain-of-thought, and reasoning in VLMs. Finally, we analyse the challenges inherent to visual grounding and suggest promising directions for future research.