This study investigates the behavior of model-integrated routers in Mixture of Experts (MoE) models, focusing on how tokens are routed based on their linguistic features, specifically Part-of-Speech (POS) tags. The goal is to explore across different MoE architectures whether experts specialize in processing tokens with similar linguistic traits. By analyzing token trajectories across experts and layers, we aim to uncover how MoE models handle linguistic information. Findings from six popular MoE models reveal expert specialization for specific POS categories, with routing paths showing high predictive accuracy for POS, highlighting the value of routing paths in characterizing tokens.

Discussions of statistical criteria for fairness commonly convey the normative significance of calibration within groups by invoking what risk scores "mean." On the Same Meaning picture, group-calibrated scores "mean the same thing" (on average) across individuals from different groups and accordingly, guard against disparate treatment of individuals based on group membership. My contention is that calibration guarantees no such thing. Since concrete actual people belong to many groups, calibration cannot ensure the kind of consistent score interpretation that the Same Meaning picture implies matters for fairness, unless calibration is met within every group to which an individual belongs. Alas only perfect predictors may meet this bar. The Same Meaning picture thus commits a reference class fallacy by inferring from calibration within some group to the "meaning" or evidential value of an individual's score, because they are a member of that group. Furthermore, the reference class answer it presumes is almost surely wrong. I then show that the reference class problem besets not just calibration but all group statistical facts that claim a close connection to fairness. Reflecting on the origins of this error opens a wider lens onto the predominant methodology in algorithmic fairness based on stylized cases.

Robotic dexterous grasping is a key step toward human-like manipulation. To fully unleash the potential of data-driven models for dexterous grasping, a large-scale, high-quality dataset is essential. While gradient-based optimization offers a promising way for constructing such datasets, existing works suffer from limitations, such as restrictive assumptions in energy design or limited experiments on small object sets. Moreover, the lack of a standard benchmark for comparing synthesis methods and datasets hinders progress in this field. To address these challenges, we develop a highly efficient synthesis system and a comprehensive benchmark with MuJoCo for dexterous grasping. Our system formulates grasp synthesis as a bilevel optimization problem, combining a novel lower-level quadratic programming (QP) with an upper-level gradient descent process. By leveraging recent advances in CUDA-accelerated robotic libraries and GPU-based QP solvers, our system can parallelize thousands of grasps and synthesize over 49 grasps per second on a single NVIDIA 3090 GPU. Our synthesized grasps for Shadow Hand and Allegro Hand achieve a success rate above 75% in MuJoCo, with a penetration depth and contact distance of under 1 mm, outperforming existing baselines on nearly all metrics. Compared to the previous large-scale dataset, DexGraspNet, our dataset significantly improves the performance of learning models, with a simulation success rate from around 40% to 80%. Real-world testing of the trained model on the Shadow Hand achieves an 81% success rate across 20 diverse objects.

Websites, as essential digital assets, are highly vulnerable to cyberattacks because of their high traffic volume and the significant impact of breaches. This study aims to enhance the identification of web traffic attacks by leveraging machine learning techniques. A methodology was proposed to extract relevant features from HTTP traces using the CSIC2010 v2 dataset, which simulates e-commerce web traffic. Ensemble methods, such as Random Forest and Extreme Gradient Boosting, were employed and compared against baseline classifiers, including k-nearest Neighbor, LASSO, and Support Vector Machines. The results demonstrate that the ensemble methods outperform baseline classifiers by approximately 20% in predictive accuracy, achieving an Area Under the ROC Curve (AUC) of 0.989. Feature selection methods such as Information Gain, LASSO, and Random Forest further enhance the robustness of these models. This study highlights the efficacy of ensemble models in improving attack detection while minimizing performance variability, offering a practical framework for securing web traffic in diverse application contexts.

In recent years, ML algorithms have been shown to be useful for predicting diseases based on health data and posed a potential application area for these algorithms such as modeling of diseases. The majority of these applications employ supervised rather than unsupervised ML algorithms. In addition, each year, the amount of data in medical science grows rapidly. Moreover, these data include clinical and Patient-Related Factors (PRF), such as height, weight, age, other physical characteristics, blood sugar, lipids, insulin, etc., all of which will change continually over time. Analysis of historical data can help identify disease risk factors and their interactions, which is useful for disease diagnosis and prediction. This wealth of valuable information in these data will help doctors diagnose accurately and people can become more aware of the risk factors and key indicators to act proactively. The purpose of this study is to use six supervised ML approaches to fill this gap by conducting a comprehensive experiment to investigate the correlation between PRF and Diabetes, Stroke, Heart Disease (HD), and Kidney Disease (KD). Moreover, it will investigate the link between Diabetes, Stroke, and KD and PRF with HD. Further, the research aims to compare and evaluate various ML algorithms for classifying diseases based on the PRF. Additionally, it aims to compare and evaluate ML algorithms for classifying HD based on PRF as well as Diabetes, Stroke, Asthma, Skin Cancer, and KD as attributes. Lastly, HD predictions will be provided through a Web-based application on the most accurate classifier, which allows the users to input their values and predict the output.

We study the problem of predictive runtime monitoring of black-box dynamical systems with quantitative safety properties. The black-box setting stipulates that the exact semantics of the dynamical system and the controller are unknown, and that we are only able to observe the state of the controlled (aka, closed-loop) system at finitely many time points. We present a novel framework for predicting future states of the system based on the states observed in the past. The numbers of past states and of predicted future states are parameters provided by the user. Our method is based on a combination of Taylor's expansion and the backward difference operator for numerical differentiation. We also derive an upper bound on the prediction error under the assumption that the system dynamics and the controller are smooth. The predicted states are then used to predict safety violations ahead in time. Our experiments demonstrate practical applicability of our method for complex black-box systems, showing that it is computationally lightweight and yet significantly more accurate than the state-of-the-art predictive safety monitoring techniques.

Recent advancements in deep learning have shown transformative potential in medical imaging, yet concerns about fairness persist due to performance disparities across demographic subgroups. Existing methods aim to address these biases by mitigating sensitive attributes in image data; however, these attributes often carry clinically relevant information, and their removal can compromise model performance-a highly undesirable outcome. To address this challenge, we propose Fair Re-fusion After Disentanglement (FairREAD), a novel, simple, and efficient framework that mitigates unfairness by re-integrating sensitive demographic attributes into fair image representations. FairREAD employs orthogonality constraints and adversarial training to disentangle demographic information while using a controlled re-fusion mechanism to preserve clinically relevant details. Additionally, subgroup-specific threshold adjustments ensure equitable performance across demographic groups. Comprehensive evaluations on a large-scale clinical X-ray dataset demonstrate that FairREAD significantly reduces unfairness metrics while maintaining diagnostic accuracy, establishing a new benchmark for fairness and performance in medical image classification.

Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples, and the application of these methods to large language model (LLM) outputs could significantly advance model transparency and data curation. However, it has been challenging to date to apply these methods to the full scale of LLM pretraining. In this paper, we refine existing gradient-based methods to work effectively at scale, allowing us to retrieve influential examples for an 8B-parameter language model from a pretraining corpus of over 160B tokens with no need for subsampling or pre-filtering. Our method combines several techniques, including optimizer state correction, a task-specific Hessian approximation, and normalized encodings, which we find to be critical for performance at scale. In quantitative evaluations on a fact tracing task, our method performs best at identifying examples that influence model predictions, but classical, model-agnostic retrieval methods such as BM25 still perform better at finding passages which explicitly contain relevant facts. These results demonstrate a misalignment between factual *attribution* and causal *influence*. With increasing model size and training tokens, we find that influence more closely aligns with factual attribution. Finally, we examine different types of examples identified as influential by our method, finding that while many directly entail a particular fact, others support the same output by reinforcing priors on relation types, common entities, and names. We release our prompt set and model outputs, along with a web-based visualization tool to explore influential examples for factual predictions, commonsense reasoning, arithmetic, and open-ended generation for an 8B-parameter LLM.

Background: Despite the current ubiquity of Large Language Models (LLMs) across the medical domain, there is a surprising lack of studies which address their reasoning behaviour. We emphasise the importance of understanding reasoning behaviour as opposed to high-level prediction accuracies, since it is equivalent to explainable AI (XAI) in this context. In particular, achieving XAI in medical LLMs used in the clinical domain will have a significant impact across the healthcare sector. Results: Therefore, we define the concept of reasoning behaviour in the specific context of medical LLMs. We then categorise and discuss the current state of the art of methods which evaluate reasoning behaviour in medical LLMs. Finally, we propose theoretical frameworks which can empower medical professionals or machine learning engineers to gain insight into the low-level reasoning operations of these previously obscure models. Conclusion: The subsequent increased transparency and trust in medical machine learning models by clinicians as well as patients will accelerate the integration, application as well as further development of medical AI for the healthcare system as a whole

Funding and support: The Generative AI Challenge is funded by grants from the Future Health Research and Innovation Fund (FHRIF), Grant ID IC2023-GAIA/11. Conflict of interest statement: The authors declare no conflicts of interest. Abstract This exploratory pilot study investigated the potential of combining a domain-specific model, BERN2, with large language models (LLMs) to enhance automated disease phenotyping from research survey data. Motivated by the need for efficient and accurate methods to harmonize the growing volume of survey data with standardized disease ontologies, we employed BERN2, a biomedical named entity recognition and normalization model, to extract disease information from the ORIGINS birth cohort survey data. After rigorously evaluating BERN2's performance against a manually curated ground truth dataset, we integrated various LLMs using prompt engineering, Retrieval-Augmented Generation (RAG), and Instructional Fine-Tuning (IFT) to refine the model's outputs. BERN2 demonstrated high performance in extracting and normalizing disease mentions, and the integration of LLMs, particularly with Few Shot Inference and RAG orchestration, further improved accuracy. This approach, especially when incorporating structured examples, logical reasoning prompts, and detailed context, offers a promising avenue for developing tools to enable efficient cohort profiling and data harmonization across large, heterogeneous research datasets. Introduction The increasing availability of research survey data from cohort studies and clinical trials offers unprecedented opportunities to advance biomedical research and improve healthcare (1).