The Consolidated Standards of Reporting Trials statement is the global benchmark for transparent and high-quality reporting of randomized controlled trials. Manual verification of CONSORT adherence is a laborious, time-intensive process that constitutes a significant bottleneck in peer review and evidence synthesis. This study aimed to systematically evaluate the accuracy and reliability of contemporary LLMs in identifying the adherence of published RCTs to the CONSORT 2010 statement under a zero-shot setting. We constructed a golden standard dataset of 150 published RCTs spanning diverse medical specialties. The primary outcome was the macro-averaged F1-score for the three-class classification task, supplemented by item-wise performance metrics and qualitative error analysis. Overall model performance was modest. The top-performing models, Gemini-2.5-Flash and DeepSeek-R1, achieved nearly identical macro F1 scores of 0.634 and Cohen's Kappa coefficients of 0.280 and 0.282, respectively, indicating only fair agreement with expert consensus. A striking performance disparity was observed across classes: while most models could identify compliant items with high accuracy (F1 score > 0.850), they struggled profoundly with identifying non-compliant and not applicable items, where F1 scores rarely exceeded 0.400. Notably, some high-profile models like GPT-4o underperformed, achieving a macro F1-score of only 0.521. LLMs show potential as preliminary screening assistants for CONSORT checks, capably identifying well-reported items. However, their current inability to reliably detect reporting omissions or methodological flaws makes them unsuitable for replacing human expertise in the critical appraisal of trial quality.

Multi-agent reinforcement learning (MARL) has shown promise for large-scale network control, yet existing methods face two major limitations. First, they typically rely on assumptions leading to decay properties of local agent interactions, limiting their ability to capture long-range dependencies such as cascading power failures or epidemic outbreaks. Second, most approaches lack generalizability across network topologies, requiring retraining when applied to new graphs. We introduce STACCA (Shared Transformer Actor-Critic with Counterfactual Advantage), a unified transformer-based MARL framework that addresses both challenges. STACCA employs a centralized Graph Transformer Critic to model long-range dependencies and provide system-level feedback, while its shared Graph Transformer Actor learns a generalizable policy capable of adapting across diverse network structures. Further, to improve credit assignment during training, STACCA integrates a novel counterfactual advantage estimator that is compatible with state-value critic estimates. We evaluate STACCA on epidemic containment and rumor-spreading network control tasks, demonstrating improved performance, network generalization, and scalability. These results highlight the potential of transformer-based MARL architectures to achieve scalable and generalizable control in large-scale networked systems.

Abstract--Autonomous underwater vehicles rely on precise navigation systems that combine the inertial navigation system and the Doppler velocity log for successful missions in challenging environments where satellite navigation is unavailable. The effectiveness of this integration critically depends on accurate alignment between the sensor reference frames. Standard model-based alignment methods between these sensor systems suffer from lengthy convergence times, dependence on prescribed motion patterns, and reliance on external aiding sensors, significantly limiting operational flexibility. T o address these limitations, this paper presents ResAlignNet, a data-driven approach using the 1D ResNet-18 architecture that transforms the alignment problem into deep neural network optimization, operating as an in-situ solution that requires only sensors on board without external positioning aids or complex vehicle maneuvers, while achieving rapid convergence in seconds. Additionally, the approach demonstrates the learning capabilities of Sim2Real transfer, enabling training in synthetic data while deploying in operational sensor measurements. Experimental validation using the Snapir autonomous underwater vehicle demonstrates that ResAlignNet achieves alignment accuracy within 0.8 using only 25 seconds of data collection, representing a 65% reduction in convergence time compared to standard velocity-based methods. The trajectory-independent solution eliminates motion pattern requirements and enables immediate vehicle deployment without lengthy pre-mission procedures, advancing underwater navigation capabilities through robust sensor-agnostic alignment that scales across different operational scenarios and sensor specifications. Underwater navigation systems are critical for a wide range of marine applications, particularly autonomous underwater vehicles (AUVs) operating in challenging environments where global navigation satellite systems (GNSSs) are unavailable [1].

Graphical User Interface (GUI) grounding - the task of mapping natural language instructions to screen coordinates - is essential for autonomous agents and accessibility technologies. Existing systems rely on monolithic models or one-shot pipelines that lack modularity and fail under visual clutter and ambiguous instructions. We introduce MEGA-GUI, a multi-stage framework that separates grounding into coarse Region-of-Interest (ROI) selection and fine-grained element grounding, orchestrated by specialized vision-language agents. MEGA-GUI features a bidirectional ROI zoom algorithm that mitigates spatial dilution and a context-aware rewriting agent that reduces semantic ambiguity. Our analysis reveals complementary strengths and weaknesses across vision-language models at different visual scales, and we show that leveraging this modular structure achieves consistently higher accuracy than monolithic approaches. On the visually dense ScreenSpot-Pro benchmark, MEGA-GUI attains 73.18% accuracy, and on the semantically complex OSWorld-G benchmark it reaches 68.63%, surpassing previously reported results. Code and the Grounding Benchmark Toolkit (GBT) are available at https://github.com/samsungsds-research-papers/mega-gui.

Early diagnosis of breast cancer is crucial, enabling the establishment of appropriate treatment plans and markedly enhancing patient prognosis. While direct magnetic resonance imaging-guided biopsy demonstrates promising performance in detecting cancer lesions, its practical application is limited by prolonged procedure times and high costs. To overcome these issues, an indirect MRI-guided biopsy that allows the procedure to be performed outside of the MRI room has been proposed, but it still faces challenges in creating an accurate real-time deformable breast model. In our study, we tackled this issue by developing a graph neural network (GNN)-based model capable of accurately predicting deformed breast cancer sites in real time during biopsy procedures. An individual-specific finite element (FE) model was developed by incorporating magnetic resonance (MR) image-derived structural information of the breast and tumor to simulate deformation behaviors. A GNN model was then employed, designed to process surface displacement and distance-based graph data, enabling accurate prediction of overall tissue displacement, including the deformation of the tumor region. The model was validated using phantom and real patient datasets, achieving an accuracy within 0.2 millimeters (mm) for cancer node displacement (RMSE) and a dice similarity coefficient (DSC) of 0.977 for spatial overlap with actual cancerous regions. Additionally, the model enabled real-time inference and achieved a speed-up of over 4,000 times in computational cost compared to conventional FE simulations. The proposed deformation-aware GNN model offers a promising solution for real-time tumor displacement prediction in breast biopsy, with high accuracy and real-time capability. Its integration with clinical procedures could significantly enhance the precision and efficiency of breast cancer diagnosis.

Emergency Medical Technicians (EMTs) operate in high-pressure environments, making rapid, life-critical decisions under heavy cognitive and operational loads. We present EMSGlass, a smart-glasses system powered by EMSNet, the first multimodal multitask model for Emergency Medical Services (EMS), and EMSServe, a low-latency multimodal serving framework tailored to EMS scenarios. EMSNet integrates text, vital signs, and scene images to construct a unified real-time understanding of EMS incidents. Trained on real-world multimodal EMS datasets, EMSNet simultaneously supports up to five critical EMS tasks with superior accuracy compared to state-of-the-art unimodal baselines. Built on top of PyTorch, EMSServe introduces a modality-aware model splitter and a feature caching mechanism, achieving adaptive and efficient inference across heterogeneous hardware while addressing the challenge of asynchronous modality arrival in the field. By optimizing multimodal inference execution in EMS scenarios, EMSServe achieves 1.9x -- 11.7x speedup over direct PyTorch multimodal inference. A user study evaluation with six professional EMTs demonstrates that EMSGlass enhances real-time situational awareness, decision-making speed, and operational efficiency through intuitive on-glass interaction. In addition, qualitative insights from the user study provide actionable directions for extending EMSGlass toward next-generation AI-enabled EMS systems, bridging multimodal intelligence with real-world emergency response workflows.

Low-cost micro-electromechanical accelerometers are widely used in navigation, robotics, and consumer devices for motion sensing and position estimation. However, their performance is often degraded by bias errors. To eliminate deterministic bias terms a calibration procedure is applied under stationary conditions. It requires accelerom- eter leveling or complex orientation-dependent calibration procedures. To overcome those requirements, in this paper we present a model-free learning-based calibration method that estimates accelerometer bias under stationary conditions, without requiring knowledge of the sensor orientation and without the need to rotate the sensors. The proposed approach provides a fast, practical, and scalable solution suitable for rapid field deployment. Experimental validation on a 13.39-hour dataset collected from six accelerometers shows that the proposed method consistently achieves error levels more than 52% lower than traditional techniques. On a broader scale, this work contributes to the advancement of accurate calibration methods in orientation-free scenarios. As a consequence, it improves the reliability of low-cost inertial sensors in diverse scientific and industrial applications and eliminates the need for leveled calibration.

Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under the low and unstructured sparsity (30-90%) commonly observed in pruned LLMs, unstructured pruning provided only limited memory reduction and speedup. We propose MACKO-SpMV, a GPU-optimized format and kernel co-designed to reduce storage overhead while preserving compatibility with the GPU's execution model. This enables efficient SpMV for unstructured sparsity without specialized hardware units (e.g., tensor cores) or format-specific precomputation. Empirical results show that at sparsity 50%, MACKO is the first approach with significant 1.5x memory reduction and 1.2-1.5x speedup over dense representation. Speedups over other SpMV baselines: 2.8-13.0x over cuSPARSE, 1.9-2.6x over Sputnik, and 2.2-2.5x over DASP. Applied to Llama2-7B pruned with Wanda to sparsity 50%, it delivers 1.5x memory reduction and 1.5x faster inference at fp16 precision. Thanks to MACKO, unstructured pruning at 50% sparsity is now justified in real-world LLM workloads.

Language models (LMs) are often adapted through supervised fine-tuning (SFT) to specialize their capabilities for downstream tasks. However, in typical scenarios where the fine-tuning data is limited, e.g., compared to pre-training, SFT can lead LMs to overfit, causing them to rely on spurious patterns within the target task or to compromise other broadly useful capabilities as a side effect of narrow specialization. In this paper, we propose Learning-from-the-Undesirable (LfU), a simple yet effective regularization scheme for SFT to mitigate overfitting issues when fine-tuning LMs with limited data. Specifically, we aim to regularize the fine-tuning process to favor solutions that are resilient to "undesirable" model updates, e.g., gradient ascent steps that steer the model toward undesirable behaviors. To this end, we propose a novel form of consistency regularization that directly aligns internal representations of the model with those after an undesirable update. By leveraging representation-level data augmentation through undesirable updates, LfU effectively promotes generalization under limited data. Our experiments on diverse LM downstream tasks show that LfU serves as an effective prior that enhances adaptability while preserving pretrained knowledge. For example, our LM from LfU achieves a 16.8% average improvement on math tasks compared to vanilla SFT on the same dataset, where the latter even leads to degraded performance on those tasks. Furthermore, LfU exhibits improved robustness to prompt variations, e.g., yielding a 92.1% lower standard deviation in output performances compared to SFT, highlighting its versatile effects.

We introduce AA-Omniscience, a benchmark designed to measure both factual recall and knowledge calibration across 6,000 questions. Questions are derived from authoritative academic and industry sources, and cover 42 economically relevant topics within six different domains. The evaluation measures a model's Omniscience Index, a bounded metric (-100 to 100) measuring factual recall that jointly penalizes hallucinations and rewards abstention when uncertain, with 0 equating to a model that answers questions correctly as much as it does incorrectly. Among evaluated models, Claude 4.1 Opus attains the highest score (4.8), making it one of only three models to score above zero. These results reveal persistent factuality and calibration weaknesses across frontier models. Performance also varies by domain, with the models from three different research labs leading across the six domains. This performance variability suggests models should be chosen according to the demands of the use case rather than general performance for tasks where knowledge is important.