Hospital patient falls remain a critical and costly challenge worldwide. While conventional fall prevention systems typically rely on post-fall detection or reactive alerts, they also often suffer from high false positive rates and fail to address the underlying patient needs that lead to bed-exit attempts. This paper presents a novel system architecture that leverages the Internet of Robotic Things (IoRT) to orchestrate human-robot-robot interaction for proactive and personalized patient assistance. The system integrates a privacy-preserving thermal sensing model capable of real-time bed-exit prediction, with two coordinated robotic agents that respond dynamically based on predicted intent and patient input. This orchestrated response could not only reduce fall risk but also attend to the patient's underlying motivations for movement, such as thirst, discomfort, or the need for assistance, before a hazardous situation arises. Our contributions with this pilot study are three-fold: (1) a modular IoRT-based framework enabling distributed sensing, prediction, and multi-robot coordination; (2) a demonstration of low-resolution thermal sensing for accurate, privacy-preserving preemptive bed-exit detection; and (3) results from a user study and systematic error analysis that inform the design of situationally aware, multi-agent interactions in hospital settings. The findings highlight how interactive and connected robotic systems can move beyond passive monitoring to deliver timely, meaningful assistance, empowering safer, more responsive care environments.

Due to the complex and resource-intensive nature of diagnosing Autism Spectrum Condition (ASC), several computer-aided diagnostic support methods have been proposed to detect autism by analyzing behavioral cues in patient video data. While these models show promising results on some datasets, they struggle with poor gaze feature performance and lack of real-world generalizability. To tackle these challenges, we analyze a standardized video dataset comprising 168 participants with ASC (46% female) and 157 non-autistic participants (46% female), making it, to our knowledge, the largest and most balanced dataset available. We conduct a multimodal analysis of facial expressions, voice prosody, head motion, heart rate variability (HRV), and gaze behavior. To address the limitations of prior gaze models, we introduce novel statistical descriptors that quantify variability in eye gaze angles, improving gaze-based classification accuracy from 64% to 69% and aligning computational findings with clinical research on gaze aversion in ASC. Using late fusion, we achieve a classification accuracy of 74%, demonstrating the effectiveness of integrating behavioral markers across multiple modalities. Our findings highlight the potential for scalable, video-based screening tools to support autism assessment.

End-to-end multi-modal planning has become a transformative paradigm in autonomous driving, effectively addressing behavioral multi-modality and the generalization challenge in long-tail scenarios. We propose AnchDrive, a framework for end-to-end driving that effectively bootstraps a diffusion policy to mitigate the high computational cost of traditional generative models. Rather than denoising from pure noise, AnchDrive initializes its planner with a rich set of hybrid trajectory anchors. These anchors are derived from two complementary sources: a static vocabulary of general driving priors and a set of dynamic, context-aware trajectories. The dynamic trajectories are decoded in real-time by a Transformer that processes dense and sparse perceptual features. The diffusion model then learns to refine these anchors by predicting a distribution of trajectory offsets, enabling fine-grained refinement. This anchor-based bootstrapping design allows for efficient generation of diverse, high-quality trajectories. Experiments on the NAVSIM benchmark confirm that AnchDrive sets a new state-of-the-art and shows strong generalizability

MIDOG 2025 Track 1 requires mitosis detection in whole-slideimages (WSIs) containing non-tumor, inflamed, and necrotic re-gions. Due to the complicated and heterogeneous context, aswell as possible artifacts, there are often false positives and falsenegatives, thus degrading the detection F1-score. To addressthis problem, we propose a two-stage framework. Firstly, an im-proved YOLO11x, integrated with EMA attention and LSConv,is employed to generate mitosis candidates. We use a low confi-dence threshold to generate as many proposals as possible, en-suring the detection recall. Then, a ConvNeXt-Tiny classifieris employed to filter out the false positives, ensuring the detec-tion precision. Consequently, the proposed two-stage frame-work can generate a high detection F1-score. Evaluated on afused dataset comprising MIDOG++, MITOS_WSI_CCMCT,and MITOS_WSI_CMC, our framework achieves an F1-scoreof 0.882, which is 0.035 higher than the single-stage YOLO11xbaseline. This performance gain is produced by a significantprecision improvement, from 0.762 to 0.839, and a comparablerecall. On the MIDOG 2025 Track 1 preliminary test set, thealgorithm scores an F1 score of 0.7587. The code is available athttps://github.com/xxiao0304/MIDOG-2025-Track-1-of-SZTU.

Current benchmarks for evaluating Large Language Models (LLMs) often do not exhibit enough writing style diversity, with many adhering primarily to standardized conventions. Such benchmarks do not fully capture the rich variety of communication patterns exhibited by humans. Thus, it is possible that LLMs, which are optimized on these benchmarks, may demonstrate brittle performance when faced with "non-standard" input. In this work, we test this hypothesis by rewriting evaluation prompts using persona-based LLM prompting, a low-cost method to emulate diverse writing styles. Our results show that, even with identical semantic content, variations in writing style and prompt formatting significantly impact the estimated performance of the LLM under evaluation. Notably, we identify distinct writing styles that consistently trigger either low or high performance across a range of models and tasks, irrespective of model family, size, and recency. Our work offers a scalable approach to augment existing benchmarks, improving the external validity of the assessments they provide for measuring LLM performance across linguistic variations.

Latent-space monitors aim to detect undesirable behaviours in Large Language Models by leveraging their internal representations rather than relying solely on black-box outputs. These methods have shown promise in identifying behaviours such as deception and unsafe completions. However, these monitors may themselves become training signals, for example, by using problematic samples found in deployment to retrain models. This raises an important question: can models learn to evade such monitors? To evaluate this capability, we introduce RL-Obfuscation, in which LLMs are finetuned via reinforcement learning to evade latent-space monitors while maintaining their blackbox behaviour. We apply RL-Obfuscation to Language Models ranging from 7B to 14B parameters and evaluate their Evasion Success Rate against a suite of monitors. We find that token-level monitors are highly vulnerable to this attack while more holistic monitors, such as max-pooling or attention-based probes, remain robust. Moreover, for these vulnerable monitors, models trained to evade a single static monitor can generalise to evade other unseen monitors. We also find that the models can be trained to conditionally bypass latent-space monitors on only certain inputs. Finally, we study how the models bypass these monitors and find that the model can learn to repurpose tokens to have different internal representations.

Multimodal electronic health record (EHR) data is useful for disease risk prediction based on medical domain knowledge. However, general medical knowledge must be adapted to specific healthcare settings and patient populations to achieve practical clinical use. Additionally, risk prediction systems must handle uncertainty from incomplete data and non-deterministic health outcomes while remaining explainable. These challenges can be alleviated by the integration of knowledge graphs (KGs) and Bayesian networks (BNs). We present a novel approach for constructing BNs from ontology-based KGs and multimodal EHR data for explainable disease risk prediction. Through an application use case of atrial fibrillation and real-world EHR data, we demonstrate that the approach balances generalised medical knowledge with patient-specific context, effectively handles uncertainty, is highly explainable, and achieves good predictive performance.

Vocal health plays a crucial role in peoples' lives, significantly impacting their communicative abilities and interactions. However, despite the global prevalence of voice disorders, many lack access to convenient diagnosis and treatment. This paper introduces VocalAgent, an audio large language model (LLM) to address these challenges through vocal health diagnosis. We leverage Qwen-Audio-Chat fine-tuned on three datasets collected in-situ from hospital patients, and present a multifaceted evaluation framework encompassing a safety assessment to mitigate diagnostic biases, cross-lingual performance analysis, and modality ablation studies. VocalAgent demonstrates superior accuracy on voice disorder classification compared to state-of-the-art baselines. Its LLM-based method offers a scalable solution for broader adoption of health diagnostics, while underscoring the importance of ethical and technical validation.

While Large Language Models (LLMs) have demonstrated impressive capabilities, their output quality remains inconsistent across various application scenarios, making it difficult to identify trustworthy responses, especially in complex tasks requiring multi-step reasoning. In this paper, we propose a Token-level Uncertainty estimation framework for Reasoning (TokUR) that enables LLMs to self-assess and self-improve their responses in mathematical reasoning. Specifically, we introduce low-rank random weight perturbation during LLM decoding to generate predictive distributions for token-level uncertainty estimation, and we aggregate these uncertainty quantities to capture the semantic uncertainty of generated responses. Experiments on mathematical reasoning datasets of varying difficulty demonstrate that TokUR exhibits a strong correlation with answer correctness and model robustness, and the uncertainty signals produced by TokUR can be leveraged to enhance the model's reasoning performance at test time. These results highlight the effectiveness of TokUR as a principled and scalable approach for improving the reliability and interpretability of LLMs in challenging reasoning tasks.

Federated Learning (FL) has emerged as a promising decentralized learning (DL) approach that enables the use of distributed data without compromising user privacy. However, FL poses several key challenges. First, it is frequently assumed that every client can train the same machine learning models, however, not all clients are able to meet this assumption because of differences in their business needs and computational resources. Second, statistical heterogeneity (a.k.a. non-IID data) poses a major challenge in FL, which can lead to lower global model performance. Third, while addressing these challenges, there is a need for a cost-effective incentive mechanism to encourage clients to participate in FL training. In response to these challenges, we propose several methodologies: DL-SH, which facilitates efficient, privacy-preserving, and communication-efficient learning in the context of statistical heterogeneity; DL-MH, designed to manage fully heterogeneous models while tackling statistical disparities; and I-DL-MH, an incentive-based extension of DL-MH that promotes client engagement in federated learning training by providing incentives within this complex federated learning framework. Comprehensive experiments were carried out to assess the performance and scalability of the proposed approaches across a range of complex experimental settings. This involved utilizing various model architectures, in diverse data distributions, including IID and several non-IID scenarios, as well as multiple datasets. Experimental results demonstrate that the proposed approaches significantly enhance accuracy and decrease communication costs while effectively addressing statistical heterogeneity and model heterogeneity in comparison to existing state-of-the-art approaches and baselines, with DL-SH improving global model accuracy by 153%, and I-DL-MH achieving a 225% improvement under non-IID conditions.