i-2-0

Documents about i-2-0

• From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia#1105302arXiv (All)
• Partner-Specific Affective Precision in Social Active Inference#1051274arXiv (All)
• Improving Fairness with Ensemble Combination: Margin-Dependent Bounds#972839arXiv (All)
• How Metacognitive Architectures Remember Their Own Thoughts: A Systematic Review#1049622arXiv (All)
• A framework for auditing grounding claims#1155086arXiv (All)
• Facile synthesis and phase stability of Cu-based Na₂Cu(SO₄)₂·<i>x</i>H₂O (<i>x</i> = 0–2) sulfate minerals as conversion type battery electrodes#398773HAL (France)
• Measuring Model-Induced Discrimination via Efficient Fairness Approximation#972865arXiv (All)
• Measuring proximity to standard planes during fetal brain ultrasound scanning#971655arXiv (All)
• A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization#1343743arXiv (All)
• VILKEN KONSERVATISM YTTRAR SIG I TIDÖ 2.0? - EN IDEOLOGISK ANALYS AV NATIONALKONSERVATISM, REVOLUTIONÄR KONSERVATISM &amp; LIBERALKONSERVATISM I DET POLITISKA DOKUMENTET TIDÖ 2.0#185256GUPEA
• GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation#1248525arXiv (All)
• GLL: A Differentiable Graph Learning Layer for Neural Networks#1344417arXiv (All)
• Map Users and Mapmakers: The Scope of Cognitive Attribution from Acquired Representations#1083373arXiv (OAI Expanded)
• Monitoring latent reasoning in looped language models#1343316arXiv (All)
• Global epidemiology of azole resistance in <i>Aspergillus fumigatus</i>#145105HAL (France)
• GIM: Evaluating models via tasks that integrate multiple cognitive domains#664266arXiv (OAI Expanded)
• GIM: Evaluating models via tasks that integrate multiple cognitive domains#665766arXiv (All)
• Math for AI safety: an invitation for mathematicians#1011244arXiv (All)
• The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures#650906arXiv (OAI Expanded)
• The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures#652359arXiv (All)
• ICLHerd: Herding-Based Data Selection for LLMs with In-Context Learning as a Proxy#1402530arXiv (All)
• LIBERO-Pro2.0: A Benchmark for Evaluating the Robustness of Embodied Foundation Models#1389533arXiv (All)
• Revisiting <i>k</i> : Time‐varying stream litter breakdown rates#337542HAL (France)
• Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI#985589arXiv (All)
• LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification#1423316arXiv (All)
• Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence#609320arXiv (OAI Expanded)
• Persistent Memory Through Triple-Loop Consolidation Under Stochastic Unit Turnover#799988arXiv (All)
• Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?#972039arXiv (All)
• DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness#1298414arXiv (All)
• Integrally closed ideals with $e_{2}(I)=e_{1}(I)-e_{0}(I)+λ(A/I)$#821312arXiv (All)
• Personality Without Persons? A Psychometric Critique of Big Five Testing in Large Language Models#919879arXiv (OAI Expanded)
• Personality Without Persons? A Psychometric Critique of Big Five Testing in Large Language Models#924108arXiv (All)
• Matrix Aggregation Operators#1076218arXiv (All)
• From cacophony to hierarchy: a principled framework for assessing AI consciousness#1130272arXiv (All)
• Improving scoring functions for protein-protein docking with LambdaLoss#1154814arXiv (All)
• IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization#1422959arXiv (All)
• Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning#1156876arXiv (All)
• Grad-CAM for Visualizing Attention Regions of PCA and SVM Layers in Convolutional Neural Networks#1201909arXiv (All)
• The Kaleidoscopic Filter, Part I : A Structural Resolution of Restricted Integer Partitions#1109782arXiv (OAI Expanded)
• Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning#973167arXiv (All)
• Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World#611096arXiv (OAI Expanded)
• Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World#612573arXiv (All)
• 0.2-<i>μ</i>m InP/GaAsSb DHBT Transferred on Si-HR With 28 mW/<i>μ</i>m² at 94 GHz#268814HAL (France)
• COGNIT-Guard: Calibrated Standalone Direct-Decision Guardrails with Heterogeneous CPU-NPU Confidence Cascading under Explicit Latency and False-Positive Constraints#1118744arXiv (All)
• AI Should Facilitate Democratic Deliberation at Scale#1033838arXiv (All)
• Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation#996874arXiv (All)
• The Company You Keep: How LLMs Respond to Dark Triad Traits#974346arXiv (All)
• Beyond End-to-End Black Box Mapping: An Intentional Agent Framework for Cognitive-driven Facial Reaction Generation#1128690arXiv (All)
• Self-Organization from Constrained Geometric Radiation#1247548arXiv (All)
• 5<i>d</i>-mediated indirect exchange and effective spin Hamiltonians in Ce triangular-lattice delafossites#1235386HAL (France)