Abstract--This paper proposes a hardware-aware intrusion detection system (IDS) for Internet of Things (IoT) and Industrial IoT (IIoT) networks; it targets scenarios where classification is essential for fast, privacy-preserving, and resource-efficient threat detection. The goal is to optimize both tree-based machine learning (ML) models and compact deep neural networks (DNNs) within strict edge-device constraints. This allows for a fair comparison and reveals trade-offs between model families. We apply constrained grid search for tree-based classifiers and hardware-aware neural architecture search (HW-NAS) for 1D convolutional neural networks (1D-CNNs). Evaluation on the Edge-IIoTset benchmark shows that selected models meet tight flash, RAM, and compute limits: LightGBM achieves 95.3% accuracy using 75 KB flash and 1.2 K operations, while the HW-NAS-optimized CNN reaches 97.2% with 190 KB flash and 840 K floating-point operations (FLOPs). We deploy the full pipeline on a Raspberry Pi 3 B+, confirming that tree-based models operate within 30 ms and that CNNs remain suitable when accuracy outweighs latency. The widespread deployment of Internet of Things (IoT) systems has expanded the attack surface of modern networks, which now include critical infrastructure and operational environments vulnerable to advanced cyber threats [1], [2].

Phishing remains one of the most prevalent online threats, exploiting human trust to harvest sensitive credentials. Existing URL- and HTML-based detection systems struggle against obfuscation and visual deception. This paper presents \textbf{PhishSnap}, a privacy-preserving, on-device phishing detection system leveraging perceptual hashing (pHash). Implemented as a browser extension, PhishSnap captures webpage screenshots, computes visual hashes, and compares them against legitimate templates to identify visually similar phishing attempts. A \textbf{2024 dataset of 10,000 URLs} (70\%/20\%/10\% train/validation/test) was collected from PhishTank and Netcraft. Due to security takedowns, a subset of phishing pages was unavailable, reducing dataset diversity. The system achieved \textbf{0.79 accuracy}, \textbf{0.76 precision}, and \textbf{0.78 recall}, showing that visual similarity remains a viable anti-phishing measure. The entire inference process occurs locally, ensuring user privacy and minimal latency.

This paper presents an initial study performed by the MODOMA system. The MODOMA is a computational multi-agent laboratory environment for unsupervised language acquisition experiments such that acquisition is based on the interaction between two language models, an adult and a child agent. Although this framework employs statistical as well as rule-based procedures, the result of language acquisition is a knowledge-based language model, which can be used to generate and parse new utterances of the target language. This system is fully parametrized and researchers can control all aspects of the experiments while the results of language acquisition, that is, the acquired grammatical knowledge, are explicitly represented and can be consulted. Thus, this system introduces novel possibilities for conducting computational language acquisition experiments. The experiments presented by this paper demonstrate that functional and content categories can be acquired and represented by the daughter agent based on training and test data containing different amounts of exemplars generated by the adult agent. Interestingly, similar patterns, which are well-established for human-generated data, are also found for these machine-generated data. As the procedures resulted in the successful acquisition of discrete grammatical categories by the child agent, these experiments substantiate the validity of the MODOMA approach to modelling language acquisition.

Water quality monitoring is a core component of ecological environmental protection. However, due to sensor failure or other inevitable factors, data missing often exists in long-term monitoring, posing great challenges in water quality analysis. This paper proposes a Neural Tucker Convolutional Network (NTCN) model for water quality data imputation, which features the following key components: a) Encode different mode entities into respective embedding vectors, and construct a Tucker interaction tensor by outer product operations to capture the complex mode-wise feature interactions; b) Use 3D convolution to extract fine-grained spatiotemporal features from the interaction tensor. Experiments on three real-world water quality datasets show that the proposed NTCN model outperforms several state-of-the-art imputation models in terms of accuracy. In advancing the modernization drive for harmonious coexistence between humans and nature, water quality monitoring plays an irreplaceable role [1]-[7].

Existing Grammatical Error Correction (GEC) systems suffer from limited reference diversity, leading to underestimated evaluation and restricted model generalization. To address this issue, we introduce the Judge of Edit-Level Validity (JELV), an automated framework to validate correction edits from grammaticality, faithfulness, and fluency. Using our proposed human-annotated Pair-wise Edit-level Validity Dataset (PEVData) as benchmark, JELV offers two implementations: a multi-turn LLM-as-Judges pipeline achieving 90% agreement with human annotators, and a distilled DeBERTa classifier with 85% precision on valid edits. We then apply JELV to reclassify misjudged false positives in evaluation and derive a comprehensive evaluation metric by integrating false positive decoupling and fluency scoring, resulting in state-of-the-art correlation with human judgments. We also apply JELV to filter LLM-generated correction candidates, expanding the BEA19's single-reference dataset containing 38,692 source sentences. Retraining top GEC systems on this expanded dataset yields measurable performance gains. JELV provides a scalable solution for enhancing reference diversity and strengthening both evaluation and model generalization.

Large language models (LLMs) offer strong high-level planning capabilities for reinforcement learning (RL) by decomposing tasks into subgoals. However, their practical utility is limited by poor planning-execution alignment, which reflects a critical gap between abstract plans and actionable, environment-compatible behaviors. This misalignment arises from two interrelated limitations: (1) LLMs often produce subgoals that are semantically plausible but infeasible or irrelevant in the target environment due to insufficient grounding in environment-specific knowledge, and (2) single-LLM planning conflates generation with self-verification, resulting in overconfident yet unreliable subgoals that frequently fail during execution. To address these challenges, we propose Subgoal Graph-Augmented Actor-Critic-Refiner (SGA-ACR), a framework that integrates an environment-specific subgoal graph and structured entity knowledge with a multi-LLM planning pipeline that explicitly separates generation, critique, and refinement to produce executable and verifiable subgoals. A subgoal tracker further monitors execution progress, provides auxiliary rewards, and adaptively updates the subgoal graph to maintain alignment between plans and actions. Experimental results on 22 diverse tasks in the open-world game "Crafter" demonstrate the effectiveness of our proposed method.

Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings. A shared latent working memory then preserves and transfers each agent's internal representations, ensuring lossless information exchange. We provide theoretical analyses establishing that LatentMAS attains higher expressiveness and lossless information preservation with substantially lower complexity than vanilla text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS consistently outperforms strong single-model and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4x-4.3x faster end-to-end inference. These results demonstrate that our new latent collaboration framework enhances system-level reasoning quality while offering substantial efficiency gains without any additional training. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS.

Digital health interventions increasingly deliver home exercise programs via sensor-equipped devices such as smartphones, enabling remote monitoring of adherence and performance. However, current software is usually authored before clinical encounters as libraries of modules for broad impairment categories. At the point of care, clinicians can only choose from these modules and adjust a few parameters (for example, duration or repetitions). As a result, individual limitations, goals, and environmental constraints are often not reflected, limiting personalization and benefit. We propose a paradigm in which large language models (LLMs) act as constrained translators that convert clinicians' exercise prescriptions into intervention software. Clinicians remain the decision makers: they design exercises during the encounter, tailored to each patient's impairments, goals, and environment, and the LLM generates matching software. We conducted a prospective single-arm feasibility study with 20 licensed physical and occupational therapists who created 40 individualized upper extremity programs for a standardized patient; 100% of prescriptions were translated into executable software, compared with 55% under a representative template-based digital health intervention (p < 0.01). LLM-generated software correctly delivered 99.7% of instructions and monitored performance with 88.4% accuracy (95% confidence interval, 0.843-0.915). Overall, 90% of therapists judged the system safe for patient interaction and 75% expressed willingness to adopt it in practice. To our knowledge, this is the first prospective evaluation of clinician-directed intervention software generation with an LLM in health care, demonstrating feasibility and motivating larger trials in real patient populations.

Multivariate Time-Series (MTS) clustering discovers intrinsic grouping patterns of temporal data samples. Although time-series provide rich discriminative information, they also contain substantial redundancy, such as steady-state machine operation records and zero-output periods of solar power generation. Such redundancy diminishes the attention given to discriminative timestamps in representation learning, thus leading to performance bottlenecks in MTS clustering. Masking has been widely adopted to enhance the MTS representation, where temporal reconstruction tasks are designed to capture critical information from MTS. However, most existing masking strategies appear to be standalone preprocess-ing steps, isolated from the learning process, which hinders dynamic adaptation to the importance of clustering-critical timestamps. Accordingly, this paper proposes the Evolving-masked MTS Clustering (EMTC) method, whose model architecture comprises Importance-aware V ariate-wise Masking (IVM) and Multi-Endogenous Views (MEV) generation modules. IVM adaptively guides the model in learning more discriminative representations for clustering, while the reconstruction and cluster-guided contrastive learning pathways enhance and connect the representation learning to clustering tasks. Extensive experiments on 15 benchmark datasets demonstrate the superiority of EMTC over eight SOT A methods, where the EMTC achieves an average improvement of 4.85% in F1-Score over the strongest baselines.

The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Inspired by knowledge distillation, Prism leverages a powerful, instruction-following teacher LLM (FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. Our extensive experiments on benchmark datasets reveal a key finding: the distillation process not only transfers knowledge but also acts as a noise filter. Our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, demonstrating an emergent ability to correct hallucinations present in the teacher's outputs. While achieving a 24x speedup and a 10x reduction in memory consumption, our analysis validates that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality, and perhaps more importantly, trustworthy explainable recommendation.