Recent advances in 3D reconstruction techniques and vision-language models have fueled significant progress in 3D semantic understanding, a capability critical to robotics, autonomous driving, and virtual/augmented reality. However, methods that rely on 2D priors are prone to a critical challenge: cross-view semantic inconsistencies induced by occlusion, image blur, and view-dependent variations. These inconsistencies, when propagated via projection supervision, deteriorate the quality of 3D Gaussian semantic fields and introduce artifacts in the rendered outputs. To mitigate this limitation, we propose CCL-LGS, a novel framework that enforces view-consistent semantic supervision by integrating multi-view semantic cues. Specifically, our approach first employs a zero-shot tracker to align a set of SAM-generated 2D masks and reliably identify their corresponding categories. Next, we utilize CLIP to extract robust semantic encodings across views. Finally, our Contrastive Codebook Learning (CCL) module distills discriminative semantic features by enforcing intra-class compactness and inter-class distinctiveness. In contrast to previous methods that directly apply CLIP to imperfect masks, our framework explicitly resolves semantic conflicts while preserving category discriminability. Extensive experiments demonstrate that CCL-LGS outperforms previous state-of-the-art methods. Our project page is available at https://epsilontl.github.io/CCL-LGS/.

Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downstream applications. We propose a training methodology that enables forecasting models to adapt their focus to application-specific regions of interest at inference time, without retraining. The approach partitions the prediction space into fine-grained segments during training, which are dynamically reweighted and aggregated to emphasize the target range specified by the application. Unlike prior methods that predefine these ranges, our framework supports flexible, on-demand adjustments. Experiments on standard benchmarks and a newly collected wireless communication dataset demonstrate that our method not only improves forecast accuracy within regions of interest but also yields measurable gains in downstream task performance.

Semantic communication aims to convey meaning rather than bit-perfect reproduction, representing a paradigm shift from traditional communication. This paper investigates distribution learning in semantic communication where receivers must infer the underlying meaning distribution through sequential observations. While semantic communication traditionally optimizes individual meaning transmission, we establish fundamental conditions for learning source statistics when priors are unknown. We prove that learnability requires full rank of the effective transmission matrix, characterize the convergence rate of distribution estimation, and quantify how estimation errors translate to semantic distortion. Our analysis reveals a fundamental trade-off: encoding schemes optimized for immediate semantic performance often sacrifice long-term learnability. Experiments on CIFAR-10 validate our theoretical framework, demonstrating that system conditioning critically impacts both learning rate and achievable performance. These results provide the first rigorous characterization of statistical learning in semantic communication and offer design principles for systems that balance immediate performance with adaptation capability.

--The Internet of Medical Things (IoMT) has been emerging as the main driver for the healthcare revolution. These networks typically include resource-constrained, heterogeneous devices such as wearable sensors, smart pills, and implantable devices, making them vulnerable to diverse cyberattacks, e.g., denial-of-service, ransomware, data hijacking, and spoofing attacks. T o mitigate these risks, Intrusion Detection Systems (IDSs) are critical for monitoring and securing patients' medical devices. However, traditional centralized IDSs may not be suitable for IoMT due to inherent limitations such as delays in response time, privacy concerns, and increased security vulnerabilities. Specifically, centralized IDS architectures require every sensor to transmit its data to a central server, potentially causing significant delays or even disrupting network operations in densely populated areas. On the other hand, executing an IDS on IoMT devices is generally infeasible due to the lack of computational capacity. Even if some lightweight IDS components can be deployed in these devices, they must wait for the centralized IDS to provide updated models, otherwise, they will be vulnerable to zero-day attacks, posing significant risks to patient health and data security. T o address these challenges, we propose a novel multi-level IoMT IDS framework that can not only detect zero-day attacks but also differentiate between known and unknown attacks. In particular, the first layer, namely the near Edge, filters network traffic at coarse level (i.e., attack or not), by leveraging meta-learning or One Class Classification (OCC) based on the usfAD algorithm. Then, the deeper layers (e.g., far Edge and Cloud) will determine whether the attack is known or unknown, as well as the detailed type of attack. The experimental results on the latest IoMT dataset CICIoMT2024 show that our proposed solution achieves high performance, i.e., 99.77% accuracy and 97.8% F1-score. Notably, the first layer, using either meta-learning or usfAD-based OCC, can detect zero-day attacks with high accuracy without requiring new datasets of these attacks, making our approach highly applicable for the IoMT environment. Furthermore, the meta-learning approach requires less than 1% of the dataset to achieve high performance in attack detection. HE Internet of Things (IoT) represents a transformative concept where interconnected devices equipped with sensors collect, analyze, and interact with the physical environment, creating networks that serve diverse applications. The authors are with the School of Information Technology, Crown Institute of Higher Education, Australia.

Fair clustering has traditionally focused on ensuring equitable group representation or equalizing group-specific clustering costs. However, Dickerson et al. (2025) recently showed that these fairness notions may yield undesirable or unintuitive clustering outcomes and advocated for a welfare-centric clustering approach that models the utilities of the groups. In this work, we model group utilities based on both distances and proportional representation and formalize two optimization objectives based on welfare-centric clustering: the Rawlsian (Egalitarian) objective and the Utilitarian objective. We introduce novel algorithms for both objectives and prove theoretical guarantees for them. Empirical evaluations on multiple real-world datasets demonstrate that our methods significantly outperform existing fair clustering baselines.

-- In healthcare, federated learning (FL) is a widely adopted framework that enables privacy-preserving collaboration among medical institutions. With large foundation models (FMs) demonstrating impressive capabilities, using FMs in FL through cost-efficient adapter tuning has become a popular approach. Given the rapidly evolving healthcare environment, it is crucial for individual clients to quickly adapt to new tasks or diseases by tuning adapters while drawing upon past experiences. In this work, we introduce Federated Knowledge-Enhanced Initialization (FedKEI), a novel framework that leverages cross-client and cross-task transfer from past knowledge to generate informed initializations for learning new tasks with adapters. FedKEI begins with a global clustering process at the server to generalize knowledge across tasks, followed by the optimization of aggregation weights across clusters (inter-cluster weights) and within each cluster (intra-cluster weights) to personalize knowledge transfer for each new task. To facilitate more effective learning of the inter-and intra-cluster weights, we adopt a bi-level optimization scheme that collaboratively learns the global intra-cluster weights across clients and optimizes the local inter-cluster weights toward each client's task objective. Extensive experiments on three benchmark datasets of different modalities, including dermatology, chest X-rays, and retinal OCT, demonstrate FedKEI's advantage in adapting to new diseases compared to state-of-the-art methods. NTRODUCTION Manuscript submitted 2 Dec 2024. This Research is supported by the RIE2025 Industry Alignment Fund - Industry Collaboration Project (IAF-ICP) (Award No: I2301E0020) and Japan-Singapore Joint Call: Japan Science and T echnology Agency (JST) and Agency for Science, T echnology and Research (A*ST AR) 2024 (Award No: R24I6IR141), administered by A*ST AR (Corresponding author: Qing-song Wei (wei qingsong@ihpc.a-star.edu.sg)). EDERA TED learning (FL) has gained traction in healthcare by enabling collaborative model training across institutions without sharing sensitive data [1]. With large foundation models (FMs) demonstrating strong performance across various tasks [2], [3], integrating FMs into FL presents new opportunities for medical imaging [4]. A common approach involves fine-tuning pre-trained FMs for downstream tasks in FL [5], [6].

The active research topic of prompt engineering makes it evident that LLMs are sensitive to small changes in prompt wording. A portion of this can be ascribed to the inductive bias that is present in the LLM. By using an LLM's output as a portion of its prompt, we can more easily create satisfactory wording for prompts. This has the effect of creating a prompt that matches the inductive bias in model. Empirically, we show that using this Inductive Bias Extraction and Matching strategy improves LLM Likert ratings used for classification by up to 19% and LLM Likert ratings used for ranking by up to 27%.

Although appearance-based point-of-gaze (PoG) estimation has improved, the estimators still struggle to generalize across individuals due to personal differences. Therefore, person-specific calibration is required for accurate PoG estimation. However, calibrated PoG estimators are often sensitive to head pose variations. To address this, we investigate the key factors influencing calibrated estimators and explore pose-robust calibration strategies. Specifically, we first construct a benchmark, MobilePoG, which includes facial images from 32 individuals focusing on designated points under either fixed or continuously changing head poses. Using this benchmark, we systematically analyze how the diversity of calibration points and head poses influences estimation accuracy. Our experiments show that introducing a wider range of head poses during calibration improves the estimator's ability to handle pose variation. Building on this insight, we propose a dynamic calibration strategy in which users fixate on calibration points while moving their phones. This strategy naturally introduces head pose variation during a user-friendly and efficient calibration process, ultimately producing a better calibrated PoG estimator that is less sensitive to head pose variations than those using conventional calibration strategies. Codes and datasets are available at our project page.

This paper addresses source component shift adaptation, aiming to update predictions adapting to source component shifts for incoming data streams based on past training data. Existing online learning methods often fail to utilize recurring shifts effectively, while model-pool-based methods struggle to capture individual source components, leading to poor adaptation. In this paper, we propose a source component shift adaptation method via an offline decomposition and online mixing approach. We theoretically identify that the problem can be divided into two subproblems: offline source component decomposition and online mixing weight adaptation. Based on this, our method first determines prediction models, each of which learns a source component solely based on past training data offline through the EM algorithm. Then, it updates the mixing weight of the prediction models for precise prediction through online convex optimization. Thanks to our theoretical derivation, our method fully leverages the characteristics of the shifts, achieving superior adaptation performance over existing methods. Experiments conducted on various real-world regression datasets demonstrate that our method outperforms baselines, reducing the cumulative test loss by up to 67.4%.

Background: Cirrhosis is a progressive liver disease with high mortality and frequent complications, notably acute kidney injury (AKI), which occurs in up to 50% of hospitalized patients and worsens outcomes. AKI stems from complex hemodynamic, inflammatory, and metabolic changes, making early detection essential. Many predictive tools lack accuracy, interpretability, and alignment with intensive care unit (ICU) workflows. This study developed an interpretable machine learning model for early AKI prediction in critically ill patients with cirrhosis. Methods: We conducted a retrospective analysis of the MIMIC-IV v2.2 database, identifying 1240 adult ICU patients with cirrhosis and excluding those with ICU stays under 48 hours or missing key data. Laboratory and physiological variables from the first 48 hours were extracted. The pipeline included preprocessing, missingness filtering, LASSO feature selection, and SMOTE class balancing. Six algorithms-LightGBM, CatBoost, XGBoost, logistic regression, naive Bayes, and neural networks-were trained and evaluated using AUROC, accuracy, F1-score, sensitivity, specificity, and predictive values. Results: LightGBM achieved the best performance (AUROC 0.808, 95% CI 0.741-0.856; accuracy 0.704; NPV 0.911). Key predictors included prolonged partial thromboplastin time, absence of outside-facility 20G placement, low pH, and altered pO2, consistent with known cirrhosis-AKI mechanisms and suggesting actionable targets. Conclusion: The LightGBM-based model enables accurate early AKI risk stratification in ICU patients with cirrhosis using routine clinical variables. Its high negative predictive value supports safe de-escalation for low-risk patients, and interpretability fosters clinician trust and targeted prevention. External validation and integration into electronic health record systems are warranted.