arXiv:2510.21118v3 Announce Type: replace-cross Abstract: Ensuring that Large Language Models (LLMs) generate summaries faithful to a given source document is essential for real-world applications. While prior research has explored LLM faithfulness, existing benchmarks suffer from annotation ambiguity, primarily due to the ill-defined boundary of permissible external knowledge in generated outputs. For instance, common sense is […]
Stable equilibria in the Lotka-Volterra equations
arXiv:2512.13347v1 Announce Type: new Abstract: We consider the Lotka-Volterra system and provide necessary conditions for an equilibrium to be stable. Our results naturally complement earlier fundamental results by N. Adachi, Y. Takeuchi, and H. Tokumaru, who, in a series of papers, give sufficient (and for some cases necessary) conditions for the existence of a stable […]
Rethinking Popularity Bias in Collaborative Filtering via Analytical Vector Decomposition
arXiv:2512.10688v2 Announce Type: replace-cross Abstract: Popularity bias fundamentally undermines the personalization capabilities of collaborative filtering (CF) models, causing them to disproportionately recommend popular items while neglecting users’ genuine preferences for niche content. While existing approaches treat this as an external confounding factor, we reveal that popularity bias is an intrinsic geometric artifact of Bayesian Pairwise […]
neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings
arXiv:2512.13481v1 Announce Type: new Abstract: Envy is a common human behavior that shapes competitiveness and can alter outcomes in team settings. As large language models (LLMs) increasingly act on behalf of humans in collaborative and competitive workflows, there is a pressing need to evaluate whether and under what conditions they exhibit envy-like preferences. In this […]
MusicInfuser: Making Video Diffusion Listen and Dance
arXiv:2503.14505v2 Announce Type: replace-cross Abstract: We introduce MusicInfuser, an approach that aligns pre-trained text-to-video diffusion models to generate high-quality dance videos synchronized with specified music tracks. Rather than training a multimodal audio-video or audio-motion model from scratch, our method demonstrates how existing video diffusion models can be efficiently adapted to align with musical inputs. We […]
Altered oscillatory brain networks during emotional face processing in ADHD: an eLORETA and functional ICA study
arXiv:2512.13539v1 Announce Type: new Abstract: Attention-deficit/hyperactivity disorder (ADHD) is characterized by executive dysfunction and difficulties in processing emotional facial expressions, yet the large-scale neural dynamics underlying these impairments remain insufficiently understood. This study applied network-based EEG source analysis to examine oscillatory cortical activity during cognitive and emotional Go/NoGo tasks in individuals with ADHD. EEG data […]
Decoding and Engineering the Phytobiome Communication for Smart Agriculture
arXiv:2508.03584v2 Announce Type: replace-cross Abstract: Smart agriculture applications, integrating technologies like the Internet of Things and machine learning/artificial intelligence (ML/AI) into agriculture, hold promise to address modern challenges of rising food demand, environmental pollution, and water scarcity. Alongside the concept of the phytobiome, which defines the area including the plant, its environment, and associated organisms, […]
Totalitarian Technics: The Hidden Cost of AI Scribes in Healthcare
arXiv:2512.11814v1 Announce Type: cross Abstract: Artificial intelligence (AI) scribes, systems that record and summarise patient-clinician interactions, are promoted as solutions to administrative overload. This paper argues that their significance lies not in efficiency gains but in how they reshape medical attention itself. Offering a conceptual analysis, it situates AI scribes within a broader philosophical lineage […]
DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders
arXiv:2512.13690v1 Announce Type: cross Abstract: Video diffusion models have revolutionized generative video synthesis, but they are imprecise, slow, and can be opaque during generation — keeping users in the dark for a prolonged period. In this work, we propose DiffusionBrowser, a model-agnostic, lightweight decoder framework that allows users to interactively generate previews at any point […]
CR3G: Causal Reasoning for Patient-Centric Explanations in Radiology Report Generation
arXiv:2512.11830v1 Announce Type: cross Abstract: Automatic chest X-ray report generation is an important area of research aimed at improving diagnostic accuracy and helping doctors make faster decisions. Current AI models are good at finding correlations (or patterns) in medical images. Still, they often struggle to understand the deeper cause-and-effect relationships between those patterns and a […]