arXiv:2310.16472v4 Announce Type: replace-cross Abstract: We investigate semiring provenance–a successful framework originally defined in the relational database setting–for description logics. In this context, the ontology axioms are annotated with elements of a commutative semiring and these annotations are propagated to the ontology consequences in a way that reflects how they are derived. We define a […]
A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Management
arXiv:2603.27154v1 Announce Type: cross Abstract: Entity resolution — identifying database records that refer to the same real-world entity — is naturally modelled on bipartite graphs connecting entity nodes to their attribute values. Applying a message-passing neural network (MPNN) with all available extensions (reverse message passing, port numbering, ego IDs) incurs unnecessary overhead, since different entity […]
The Price of Meaning: Why Every Semantic Memory System Forgets
arXiv:2603.27116v1 Announce Type: new Abstract: Every major AI memory system in production today organises information by meaning. That organisation enables generalisation, analogy, and conceptual retrieval — but it comes at a price. We prove that the same geometric structure enabling semantic generalisation makes interference, forgetting, and false recall inescapable. We formalise this tradeoff for textitsemantically […]
Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
arXiv:2603.27240v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque and poorly controlled. In this work, we present a comprehensive framework for diagnosing and repairing unsafe channels within LVLMs (CARE). We first perform causal mediation analysis to identify neurons […]
Can Generalist Vision Language Models (VLMs) Rival Specialist Medical VLMs? Benchmarking and Strategic Insights
arXiv:2506.17337v4 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings. However, developing specialist medical VLMs requires substantial computational resources and carefully curated datasets, and it remains unclear under which conditions generalist and specialist medical VLMs each perform best. This study highlights the complementary strengths […]
GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations
arXiv:2603.27306v1 Announce Type: cross Abstract: Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompting and do not improve across repeated executions. We introduce textscGUIDE, a non-parametric policy improvement framework that enables cross-episode adaptation without weight updates by evolving a structured, state-conditioned playbook of natural-language […]
Pan-Cancer Mapping of the Tumor Immune Landscape through Metagene Clustering and Predictive Modeling
arXiv:2603.27145v1 Announce Type: new Abstract: As immunotherapies become standard cancer treatments, it is increasingly important to identify a patient’s immune profile, which encompasses the activity of immune cells within the tumor microenvironment and the presence of specific biomarkers. However, we lack mechanistic explanations drivers of immune phenotypes. Despite advances in immune profiling with high-throughput sequencing, […]
Diagnosing Non-Markovian Observations in Reinforcement Learning via Prediction-Based Violation Scoring
arXiv:2603.27389v1 Announce Type: cross Abstract: Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors frequently violate this assumption through correlated noise, latency, or partial observability. Standard performance metrics conflate Markov breakdowns with other sources of suboptimality, leaving practitioners without diagnostic tools for such violations. This paper introduces a prediction-based scoring method […]
Diffusion-Based Quality Control of Medical Image Segmentations across Organs
arXiv:2511.09588v2 Announce Type: replace-cross Abstract: Medical image segmentation using deep learning (DL) has enabled the development of automated analysis pipelines for large-scale population studies. However, state-of-the-art DL methods are prone to hallucinations, which can result in anatomically implausible segmentations. With manual correction impractical at scale, automated quality control (QC) techniques have to address the challenge. […]
Evaluating Large and Lightweight Vision Models for Irregular Component Segmentation in E-Waste Disassembly
arXiv:2603.27441v1 Announce Type: cross Abstract: Precise segmentation of irregular and densely arranged components is essential for robotic disassembly and material recovery in electronic waste (e-waste) recycling. This study evaluates the impact of model architecture and scale on segmentation performance by comparing SAM2, a transformer-based vision model, with the lightweight YOLOv8 network. Both models were trained […]
MediHive: A Decentralized Agent Collective for Medical Reasoning
arXiv:2603.27150v1 Announce Type: new Abstract: Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems often falter on complex, interdisciplinary problems requiring robust handling of uncertainty and conflicting evidence. Multi-agent systems (MAS) leveraging LLMs enable collaborative intelligence, but prevailing centralized architectures suffer from scalability bottlenecks, single points of failure, and role confusion in […]
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
arXiv:2603.27490v1 Announce Type: cross Abstract: As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory. Such static designs may work well in some states, but they cannot adapt as […]