Large language models (LLMs) have achieved remarkable success in natural language processing, yet their performance and computational costs vary significantly. LLM routers play a crucial role in dynamically balancing these tradeoffs. While previous studies have primarily focused on routing efficiency, security vulnerabilities throughout the entire LLM router life cycle, from training to inference, remain largely unexplored. In this paper, we present a comprehensive investigation into the life-cycle routing vulnerabilities of LLM routers. We evaluate both white-box and black-box adversarial robustness, as well as backdoor robustness, across several representative routing models under extensive experimental settings. Our experiments uncover several key findings: 1) Mainstream DNN-based routers tend to exhibit the weakest adversarial and backdoor robustness, largely due to their strong feature extraction capabilities that amplify vulnerabilities during both training and inference; 2) Training-free routers demonstrate the strongest robustness across different attack types, benefiting from the absence of learnable parameters that can be manipulated. These findings highlight critical security risks spanning the entire life cycle of LLM routers and provide insights for developing more robust models. In recent years, large language models (LLMs) such as GPT-3.5 (Brown et al., 2020), GPT-4 (Achiam et al., 2023), and PaLM 2 (Anil et al., 2023) have achieved significant progress in natural language processing tasks, finding widespread applications in open-domain dialogue, question answering, code generation, and other tasks (Gu, 2023; Zhuang et al., 2023; Ghosh et al., 2024). However, different LLMs vary in terms of training data, model size, and computational cost, leading to differences in their strengths, weaknesses, and overall capabilities. Generally, larger models tend to exhibit stronger performance but come with higher inference costs, whereas smaller models are more computationally efficient but have limited capability in handling complex tasks. LLM Routing (Ding et al., 2024; Ong et al., 2024; Hu et al., 2024) is a state-of-the-art optimization strategy designed to mitigate this trade-off and achieve a balance between response quality and computational cost.

The rise of online programming education has necessitated more effective, personalized interactions, a gap that PythonPal aims to fill through its innovative learning system integrated with a chatbot. This research delves into PythonPal's potential to enhance the online learning experience, especially in contexts with high student-to-teacher ratios where there is a need for personalized feedback. PythonPal's design, featuring modules for conversation, tutorials, and exercises, was evaluated through student interactions and feedback. Key findings reveal PythonPal's proficiency in syntax error recognition and user query comprehension, with its intent classification model showing high accuracy. The system's performance in error feedback, though varied, demonstrates both strengths and areas for enhancement. Student feedback indicated satisfactory query understanding and feedback accuracy but also pointed out the need for faster responses and improved interaction quality. PythonPal's deployment promises to significantly enhance online programming education by providing immediate, personalized feedback and interactive learning experiences, fostering a deeper understanding of programming concepts among students. These benefits mark a step forward in addressing the challenges of distance learning, making programming education more accessible and effective.

Computer programming represents a rapidly evolving and sought-after career path in the 21st century. Nevertheless, novice learners may find the process intimidating for several reasons, such as limited and highly competitive career opportunities, peer and parental pressure for academic success, and course difficulties. These factors frequently contribute to anxiety and eventual dropout as a result of fear. Furthermore, research has demonstrated that beginners are significantly deterred by the fear of failure, which results in programming anxiety and and a sense of being overwhelmed by intricate topics, ultimately leading to dropping out. This project undertakes an exploration beyond the scope of conventional code learning platforms by identifying and utilising effective and personalised strategies of learning. The proposed solution incorporates features such as AI-generated challenging questions, mindfulness quotes, and tips to motivate users, along with an AI chatbot that functions as a motivational aid. In addition, the suggested solution integrates personalized roadmaps and gamification elements to maintain user involvement. The project aims to systematically monitor the progress of novice programmers and enhance their knowledge of coding with a personalised, revised curriculum to help mitigate the fear of coding and boost confidence.

Objective. Large vessel occlusion (LVO) stroke presents a major challenge in clinical practice due to the potential for poor outcomes with delayed treatment. Treatment for LVO involves highly specialized care, in particular endovascular thrombectomy, and is available only at certain hospitals. Therefore, prehospital identification of LVO by emergency ambulance services, can be critical for triaging LVO stroke patients directly to a hospital with access to endovascular therapy. Clinical scores exist to help distinguish LVO from less severe strokes, but they are based on a series of examinations that can take minutes and may be impractical for patients with dementia or those who cannot follow commands due to their stroke. There is a need for a fast and reliable method to aid in the early identification of LVO. In this study, our objective was to assess the feasibility of using 30-second photoplethysmography (PPG) recording to assist in recognizing LVO stroke. Method. A total of 88 patients, including 25 with LVO, 27 with stroke mimic (SM), and 36 non-LVO stroke patients (NL), were recorded at the Liverpool Hospital emergency department in Sydney, Australia. Demographics (age, sex), as well as morphological features and beating rate variability measures, were extracted from the PPG. A binary classification approach was employed to differentiate between LVO stroke and NL+SM (NL.SM). A 2:1 train-test split was stratified and repeated randomly across 100 iterations. Results. The best model achieved a median test set area under the receiver operating characteristic curve (AUROC) of 0.77 (0.71--0.82). \textit{Conclusion.} Our study demonstrates the potential of utilizing a 30-second PPG recording for identifying LVO stroke.

This paper introduces a simulator designed for opinion dynamics researchers to model competing influences within social networks in the presence of LLM-based agents. By integrating established opinion dynamics principles with state-of-the-art LLMs, this tool enables the study of influence propagation and counter-misinformation strategies. The simulator is particularly valuable for researchers in social science, psychology, and operations research, allowing them to analyse societal phenomena without requiring extensive coding expertise. Additionally, the simulator will be openly available on GitHub, ensuring accessibility and adaptability for those who wish to extend its capabilities for their own research.

Accurate, noninvasive glioma characterization is crucial for effective clinical management. Traditional methods, dependent on invasive tissue sampling, often fail to capture the spatial heterogeneity of the tumor. While deep learning has improved segmentation and molecular profiling, few approaches simultaneously integrate tumor morphology and molecular features. Foundation deep learning models, which learn robust, task-agnostic representations from large-scale datasets, hold great promise but remain underutilized in glioma imaging biomarkers. We propose the Multi-Task SWIN-UNETR (MTS-UNET) model, a novel foundation-based framework built on the BrainSegFounder model, pretrained on large-scale neuroimaging data. MTS-UNET simultaneously performs glioma segmentation, histological grading, and molecular subtyping (IDH mutation and 1p/19q co-deletion). It incorporates two key modules: Tumor-Aware Feature Encoding (TAFE) for multi-scale, tumor-focused feature extraction and Cross-Modality Differential (CMD) for highlighting subtle T2-FLAIR mismatch signals associated with IDH mutation. The model was trained and validated on a diverse, multi-center cohort of 2,249 glioma patients from seven public datasets. MTS-UNET achieved a mean Dice score of 84% for segmentation, along with AUCs of 90.58% for IDH mutation, 69.22% for 1p/19q co-deletion prediction, and 87.54% for grading, significantly outperforming baseline models (p<=0.05). Ablation studies validated the essential contributions of the TAFE and CMD modules and demonstrated the robustness of the framework. The foundation-based MTS-UNET model effectively integrates tumor segmentation with multi-level classification, exhibiting strong generalizability across diverse MRI datasets. This framework shows significant potential for advancing noninvasive, personalized glioma management by improving predictive accuracy and interpretability.

This work suggests faster and space-efficient index construction algorithms for LSH for Euclidean distance (\textit{a.k.a.}~\ELSH) and cosine similarity (\textit{a.k.a.}~\SRP). The index construction step of these LSHs relies on grouping data points into several bins of hash tables based on their hashcode. To generate an $m$-dimensional hashcode of the $d$-dimensional data point, these LSHs first project the data point onto a $d$-dimensional random Gaussian vector and then discretise the resulting inner product. The time and space complexity of both \ELSH~and \SRP~for computing an $m$-sized hashcode of a $d$-dimensional vector is $O(md)$, which becomes impractical for large values of $m$ and $d$. To overcome this problem, we propose two alternative LSH hashcode generation algorithms both for Euclidean distance and cosine similarity, namely, \CSELSH, \HCSELSH~and \CSSRP, \HCSSRP, respectively. \CSELSH~and \CSSRP~are based on count sketch \cite{count_sketch} and \HCSELSH~and \HCSSRP~utilize higher-order count sketch \cite{shi2019higher}. These proposals significantly reduce the hashcode computation time from $O(md)$ to $O(d)$. Additionally, both \CSELSH~and \CSSRP~reduce the space complexity from $O(md)$ to $O(d)$; ~and \HCSELSH, \HCSSRP~ reduce the space complexity from $O(md)$ to $O(N \sqrt[N]{d})$ respectively, where $N\geq 1$ denotes the size of the input/reshaped tensor. Our proposals are backed by strong mathematical guarantees, and we validate their performance through simulations on various real-world datasets.

Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk preferences consistent with human expectations across different personas. Specifically, we assess whether LLM-generated responses reflect appropriate levels of risk aversion or risk-seeking behavior based on individual's persona. Our results reveal that while LLMs make reasonable decisions in simplified, personalized risk contexts, their performance declines in more complex economic decision-making tasks. To address this, we propose an alignment method designed to enhance LLM adherence to persona-specific risk preferences. Our approach improves the economic rationality of LLMs in risk-related applications, offering a step toward more human-aligned AI decision-making.

Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowledge of this drift serves two purposes: (i) Retain an accurate model and (ii) Discovery of knowledge or insights about change in the relationship between input features and output variable w.r.t. the model. Most existing works focus only on detecting model drift but offer no interpretability. In this work, we take a principled approach to study the problem of interpretable model drift detection from a risk perspective using a feature-interaction aware hypothesis testing framework, which enjoys guarantees on test power. The proposed framework is generic, i.e., it can be adapted to both classification and regression tasks. Experiments on several standard drift detection datasets show that our method is superior to existing interpretable methods (especially on real-world datasets) and on par with state-of-the-art black-box drift detection methods. We also quantitatively and qualitatively study the interpretability aspect including a case study on USENET2 dataset. We find our method focuses on model and drift sensitive features compared to baseline interpretable drift detectors.

Malicious content generated by large language models (LLMs) can pose varying degrees of harm. Although existing LLM-based moderators can detect harmful content, they struggle to assess risk levels and may miss lower-risk outputs. Accurate risk assessment allows platforms with different safety thresholds to tailor content filtering and rejection. In this paper, we introduce per-topic severity rubrics for 11 harmful topics and build BingoGuard, an LLM-based moderation system designed to predict both binary safety labels and severity levels. To address the lack of annotations on levels of severity, we propose a scalable generate-then-filter framework that first generates responses across different severity levels and then filters out low-quality responses. Using this framework, we create BingoGuardTrain, a training dataset with 54,897 examples covering a variety of topics, response severity, styles, and BingoGuardTest, a test set with 988 examples explicitly labeled based on our severity rubrics that enables fine-grained analysis on model behaviors on different severity levels. Our BingoGuard-8B, trained on BingoGuardTrain, achieves the state-of-the-art performance on several moderation benchmarks, including WildGuardTest and HarmBench, as well as BingoGuardTest, outperforming best public models, WildGuard, by 4.3\%. Our analysis demonstrates that incorporating severity levels into training significantly enhances detection performance and enables the model to effectively gauge the severity of harmful responses.