arXiv:2510.11827v1 Announce Type: cross Abstract: Node-level anomaly detection (NAD) is challenging due to diverse structural patterns and feature distributions. As such, NAD is a critical task with several applications which range from fraud detection, cybersecurity, to recommendation systems. We introduce Janus, a framework that jointly leverages Euclidean and Hyperbolic Graph Neural Networks to capture complementary […]
Hey, wait a minute: on at-issue sensitivity in Language Models
arXiv:2510.12740v1 Announce Type: cross Abstract: Evaluating the naturalness of dialogue in language models (LMs) is not trivial: notions of ‘naturalness’ vary, and scalable quantitative metrics remain limited. This study leverages the linguistic notion of ‘at-issueness’ to assess dialogue naturalness and introduces a new method: Divide, Generate, Recombine, and Compare (DGRC). DGRC (i) divides a dialogue […]
Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Tasks
arXiv:2510.11903v1 Announce Type: cross Abstract: User event modeling plays a central role in many machine learning applications, with use cases spanning e-commerce, social media, finance, cybersecurity, and other domains. User events can be broadly categorized into personal events, which involve individual actions, and relational events, which involve interactions between two users. These two types of […]
Asking Clarifying Questions for Preference Elicitation With Large Language Models
arXiv:2510.12015v1 Announce Type: new Abstract: Large Language Models (LLMs) have made it possible for recommendation systems to interact with users in open-ended conversational interfaces. In order to personalize LLM responses, it is crucial to elicit user preferences, especially when there is limited user history. One way to get more information is to present clarifying questions […]
Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors
arXiv:2510.11953v1 Announce Type: cross Abstract: Learning disentangled representations, where distinct factors of variation are captured by independent latent variables, is a central goal in machine learning. The dominant approach has been the Variational Autoencoder (VAE) framework, which uses a Kullback-Leibler (KL) divergence penalty to encourage the latent space to match a factorized Gaussian prior. In […]
Open and Sustainable AI: challenges, opportunities and the road ahead in the life sciences (October 2025 — Version 2)
arXiv:2505.16619v2 Announce Type: replace Abstract: Artificial intelligence (AI) has recently seen transformative breakthroughs in the life sciences, expanding possibilities for researchers to interpret biological information at an unprecedented capacity, with novel applications and advances being made almost daily. In order to maximise return on the growing investments in AI-based life science research and accelerate this […]
Learning Dynamics of VLM Finetuning
arXiv:2510.11978v1 Announce Type: cross Abstract: Preference-based finetuning of vision–language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as textbflearning-dynamics–aware optimization and introduce textbfCooling-Weighted DPO (CW-DPO), a two-stage recipe that explicitly models and exploits the training trajectory. textbfStage 1 performs supervised finetuning with textbfgentle negatives: textbflow-weight smoothed supervision […]
CausalTrace: A Neurosymbolic Causal Analysis Agent for Smart Manufacturing
arXiv:2510.12033v1 Announce Type: new Abstract: Modern manufacturing environments demand not only accurate predictions but also interpretable insights to process anomalies, root causes, and potential interventions. Existing AI systems often function as isolated black boxes, lacking the seamless integration of prediction, explanation, and causal reasoning required for a unified decision-support solution. This fragmentation limits their trustworthiness […]
CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
arXiv:2510.12029v1 Announce Type: cross Abstract: Recent advancements in large language models (LLMs) highlight their fluency in generating responses to diverse prompts. However, these models sometimes generate plausible yet incorrect “hallucinated” facts, undermining trust. A frequent but often overlooked cause of such errors is the use of poorly structured or vague prompts by users, leading LLMs […]
L2M-AID: Autonomous Cyber-Physical Defense by Fusing Semantic Reasoning of Large Language Models with Multi-Agent Reinforcement Learning (Preprint)
arXiv:2510.07363v2 Announce Type: replace Abstract: The increasing integration of Industrial IoT (IIoT) exposes critical cyber-physical systems to sophisticated, multi-stage attacks that elude traditional defenses lacking contextual awareness. This paper introduces L2M-AID, a novel framework for Autonomous Industrial Defense using LLM-empowered, Multi-agent reinforcement learning. L2M-AID orchestrates a team of collaborative agents, each driven by a Large […]
APCE: Adaptive Progressive Context Expansion for Long Context Processing
arXiv:2510.12051v1 Announce Type: cross Abstract: Deploying useful Long-Context Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing memory footprint due to quadratic self-attention and linear KV-cache scaling in memory as sequence length increases; (2) the ContextRot phenomena where empirical evidence suggests that transformer architecture’s performance degrades with increasing context length. Given the shared […]
Enhancing Neural Code Representation with Additional Context
arXiv:2510.12082v1 Announce Type: cross Abstract: Automated program comprehension underpins many software engineering tasks, from code summarisation to clone detection. Recent deep learning models achieve strong results but typically rely on source code alone, overlooking contextual information such as version history or structural relationships. This limits their ability to capture how code evolves and operates. We […]