Predicting molecular properties is a critical component of drug discovery. Recent advances in deep learning--particularly Graph Neural Networks (GNNs)--have enabled end-to-end learning from molecular structures, reducing reliance on manual feature engineering. However, while GNNs and self-supervised learning approaches have advanced molecular property prediction (MPP), the integration of human prior knowledge remains indispensable, as evidenced by recent methods that leverage large language models (LLMs) for knowledge extraction. Despite their strengths, LLMs are constrained by knowledge gaps and hallucinations, particularly for less-studied molecular properties. In this work, we propose a novel framework that, for the first time, integrates knowledge extracted from LLMs with structural features derived from pre-trained molecular models to enhance MPP . Our approach prompts LLMs to generate both domain-relevant knowledge and executable code for molecular vectorization, producing knowledge-based features that are subsequently fused with structural representations. We employ three state-of-the-art LLMs--GPT -4o, GPT -4.1, and DeepSeek-R1--for knowledge extraction. Extensive experiments demonstrate that our integrated method outperforms existing approaches, confirming that the combination of LLM-derived knowledge and structural information provides a robust and effective solution for MPP .

Traditional approaches to network management have been accessible only to a handful of highly-trained network operators with significant expert knowledge. This creates barriers for lay users to easily manage their networks without resorting to experts. With recent development of powerful large language models (LLMs) for language comprehension, we design a system to make network management accessible to a broader audience of non-experts by allowing users to converse with networks in natural language. To effectively leverage advancements in LLMs, we propose an agentic framework that uses an intermediate representation to streamline configuration across diverse vendor equipment, retrieves the network state from memory in real-time, and provides an interface for external feedback. We also conduct pilot studies to collect real user data of natural language utterances for network control, and present a visualization interface to facilitate dialogue-driven user interaction and enable large-scale data collection for future development. Preliminary experiments validate the effectiveness of our proposed system components with LLM integration on both synthetic and real user utterances. Through our data collection and visualization efforts, we pave the way for more effective use of LLMs and democratize network control for everyday users.

Universit e Jean Monnet Saint-Etienne, T elecom Saint-Etienne, F-42023 Saint-Etienne, France Email: {firstname.surname}@univ-st-etienne.fr Abstract--Quality of Experience (QoE) modeling is crucial for optimizing video streaming services to capture the complex relationships between different features and user experience. We propose a novel approach to QoE modeling in video streaming applications using interpretable Machine Learning (ML) techniques over raw time series data. Unlike traditional black-box approaches, our method combines Kolmogorov-Arnold Networks (KANs) as an interpretable readout on top of compact frequency-domain features, allowing us to capture temporal information while retaining a transparent and explainable model. We evaluate our method on popular datasets and demonstrate its enhanced accuracy in QoE prediction, while offering transparency and interpretability. Quality of Experience (QoE) is a crucial aspect in today's digital landscape, as it directly affects how users perceive and interact with applications and services. Defined as'the overall acceptability of an application or service, as perceived subjectively by the end user' [1], QoE is a complex and multifaceted concept that cannot be solely defined by traditional Quality of Service (QoS) metrics such as bandwidth, delay, or jitter. In the context of video streaming, for instance, perceptual quality is a critical component of QoE.

The Fast Multipole Method (FMM) is an efficient numerical algorithm for computation of long-ranged forces in $N$-body problems within gravitational and electrostatic fields. This method utilizes multipole expansions of the Green's function inherent to the underlying dynamical systems. Despite its widespread application in physics and engineering, the integration of FMM with modern machine learning architectures remains underexplored. In this work, we propose a novel neural network architecture, the Neural FMM, that integrates the information flow of the FMM into a hierarchical machine learning framework for learning the Green's operator of an Elliptic PDE. Our Neural FMM architecture leverages a hierarchical computation flow of the FMM method to split up the local and far-field interactions and efficiently learn their respective representations.

Phishing attacks targeting both organizations and individuals are becoming an increasingly significant threat as technology advances. Current automatic detection methods often lack explainability and robustness in detecting new phishing attacks. In this work, we investigate the effectiveness of character-level deep learning models for phishing detection, which can provide both robustness and interpretability. We evaluate three neural architectures adapted to operate at the character level, namely CharCNN, CharGRU, and CharBiLSTM, on a custom-built email dataset, which combines data from multiple sources. Their performance is analyzed under three scenarios: (i) standard training and testing, (ii) standard training and testing under adversarial attacks, and (iii) training and testing with adversarial examples. Aiming to develop a tool that operates as a browser extension, we test all models under limited computational resources. In this constrained setup, CharGRU proves to be the best-performing model across all scenarios. All models show vulnerability to adversarial attacks, but adversarial training substantially improves their robustness. In addition, by adapting the Gradient-weighted Class Activation Mapping (Grad-CAM) technique to character-level inputs, we are able to visualize which parts of each email influence the decision of each model. Our open-source code and data is released at https://github.com/chipermaria/every-character-counts.

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as complex logical problems, wasting resources while constraining deep inference. To overcome this, we came up with a concept of Dynamic Reasoning Chains through Depth Specialised Mixture of Experts (DS-MoE), a modular framework that extends the Mixture of Experts paradigm from width-based to depth specialised computation. DS-MoE introduces expert modules optimised for distinct reasoning depths, shallow pattern recognition, compositional reasoning, logical inference, memory integration, and meta-cognitive supervision. A learned routing network dynamically assembles custom reasoning chains, activating only the necessary experts to match input complexity. The dataset on which we trained and evaluated DS-MoE is on The Pile, an 800GB corpus covering diverse domains such as scientific papers, legal texts, programming code, and web content, enabling systematic assessment across reasoning depths. Experimental results demonstrate that DS-MoE achieves up to 16 per cent computational savings and 35 per cent faster inference compared to uniform-depth transformers, while delivering 2.8 per cent higher accuracy on complex multi-step reasoning benchmarks. Furthermore, routing decisions yield interpretable reasoning chains, enhancing transparency and scalability. These findings establish DS-MoE as a significant advancement in adaptive neural architectures, demonstrating that depth-specialised modular processing can simultaneously improve efficiency, reasoning quality, and interpretability in large-scale language models.

Recent developments in Generative AI enable creators to stylize 3D models based on text prompts. These methods change the 3D model geometry, which can compromise the model's structural integrity once fabricated. We present MechStyle, a system that enables creators to stylize 3D printable models while preserving their structural integrity. MechStyle accomplishes this by augmenting the Generative AI-based stylization process with feedback from a Finite Element Analysis (FEA) simulation. As the stylization process modifies the geometry to approximate the desired style, feedback from the FEA simulation reduces modifications to regions with increased stress. We evaluate the effectiveness of FEA simulation feedback in the augmented stylization process by comparing three stylization control strategies. We also investigate the time efficiency of our approach by comparing three adaptive scheduling strategies. Finally, we demonstrate MechStyle's user interface that allows users to generate stylized and structurally viable 3D models and provide five example applications.

Background/Purpose: Diabetes affects over 537 million people worldwide and is projected to reach 783 million by 2045. Early risk stratification can benefit from machine learning. We compare two hybrid classifiers and assess their generalizability on an external cohort. Methods: Two hybrids were built: (i) XGBoost + Random Forest (XGB-RF) and (ii) Support Vector Machine + Logistic Regression (SVM-LR). A leakage-safe, standardized pipeline (encoding, imputation, min-max scaling; SMOTE on training folds only; probability calibration for SVM) was fit on the primary dataset and frozen. Evaluation prioritized threshold-independent discrimination (AUROC/AUPRC) and calibration (Brier, slope/intercept). External validation used the PIMA cohort (N=768) with the frozen pipeline; any thresholded metrics on PIMA were computed at the default rule tau = 0.5. Results: On the primary dataset (PR baseline = 0.50), XGB-RF achieved AUROC ~0.995 and AUPRC ~0.998, outperforming SVM-LR (AUROC ~0.978; AUPRC ~0.947). On PIMA (PR baseline ~0.349), XGB-RF retained strong performance (AUROC ~0.990; AUPRC ~0.959); SVM-LR was lower (AUROC ~0.963; AUPRC ~0.875). Thresholded metrics on PIMA at tau = 0.5 were XGB-RF (Accuracy 0.960; Precision 0.941; Recall 0.944; F1 0.942) and SVM-LR (Accuracy 0.900; Precision 0.855; Recall 0.858; F1 0.857). Conclusions: Across internal and external cohorts, XGB-RF consistently dominated SVM-LR and exhibited smaller external attenuation on ROC/PR with acceptable calibration. These results support gradient-boosting-based hybridization as a robust, transferable approach for diabetes risk stratification and motivate prospective, multi-site validation with deployment-time threshold selection based on clinical trade-offs.

Despite major advances in machine translation (MT) in recent years, progress remains limited for many low-resource languages that lack large-scale training data and linguistic resources. Cantonese and Wu Chinese are two Sinitic examples, although each enjoys more than 80 million speakers around the world. In this paper, we introduce SINITICMTER-ROR, a novel dataset that builds on existing parallel corpora to provide error span, error type, and error severity annotations in machine-translated examples from English to Mandarin, Cantonese, and Wu Chinese. Our dataset serves as a resource for the MT community to utilize in fine-tuning models with error detection capabilities, supporting research on translation quality estimation, error-aware generation, and low-resource language evaluation. We report our rigorous annotation process by native speakers, with analyses on inter-annotator agreement, iterative feedback, and patterns in error type and severity.

Recent advances in multi-agent systems (MAS) enable tools for information search and ideation by assigning personas to agents. However, how users can effectively control, steer, and critically evaluate collaboration among multiple domain-expert agents remains underexplored. We present Perspectra, an interactive MAS that visualizes and structures deliberation among LLM agents via a forum-style interface, supporting @-mention to invite targeted agents, threading for parallel exploration, with a real-time mind map for visualizing arguments and rationales. In a within-subjects study with 18 participants, we compared Perspectra to a group-chat baseline as they developed research proposals. Our findings show that Perspectra significantly increased the frequency and depth of critical-thinking behaviors, elicited more interdisciplinary replies, and led to more frequent proposal revisions than the group chat condition. We discuss implications for designing multi-agent tools that scaffold critical thinking by supporting user control over multi-agent adversarial discourse.