i-2-6

Documents about i-2-6

• When Single-Dataset Conclusions Fail: A 45-Task Study of Threshold Tuning and Resampling for Imbalanced Classification#620560arXiv (All)
• Hypothesize, Evaluate, Refine: A Scientific Agent for PDE Discovery with Unknown Spatial Coefficient Fields#779418arXiv (OAI Expanded)
• Hypothesize, Evaluate, Refine: A Scientific Agent for PDE Discovery with Unknown Spatial Coefficient Fields#780793arXiv (All)
• Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer#809491arXiv (OAI Expanded)
• Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer#819487arXiv (All)
• Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe#972321arXiv (All)
• The Art of Hierarchical Competing Patterns: Gaussian Process Optimization of Hyphenation#984547arXiv (All)
• VestigeKV: The NoPE-MLA KV Cache Carries Its Own Sparse-Attention Signal in a Vestigial Branch#996951arXiv (All)
• Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy#1014403arXiv (All)
• 2 U.S.C. § 46e — Repealed. Pub. L. 92–607, ch. V, § 506(k)(6), formerly § 506(h)(6), Oct. 31, 1972, 86 Stat. 1508, renumbered § 506(i)(6), Pub. L. 95–391, title I, § 108(a), Sept. 30, 1978, 92 Stat. 773, renumbered § 506(j)(6), Pub. L. 96–3#559006US Code (LII)
• Physics Informed Differentiable Solvers for Learning Parametric Solution Manifolds in Heterogeneous Physical Systems#628042arXiv (OAI Expanded)
• Physics Informed Differentiable Solvers for Learning Parametric Solution Manifolds in Heterogeneous Physical Systems#629904arXiv (All)
• Topology-Aware Differential Privacy in Hierarchical Federated Learning#633260arXiv (OAI Expanded)
• Topology-Aware Differential Privacy in Hierarchical Federated Learning#635609arXiv (All)
• ICON Decomposition: Auditing Deep Neural Networks with Multivariate Variance-based Concept-level Explanations#808981arXiv (OAI Expanded)
• ICON Decomposition: Auditing Deep Neural Networks with Multivariate Variance-based Concept-level Explanations#818973arXiv (All)
• Heat Field Signatures: From Point Clouds to Smooth Geometry#985379arXiv (All)
• Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs#609135arXiv (OAI Expanded)
• Emergent 3D Instance Segmentation from Self-Supervised Point Transformers#616434arXiv (OAI Expanded)
• Emergent 3D Instance Segmentation from Self-Supervised Point Transformers#616934arXiv (All)
• When Retrieval Fails Before It Begins: Structurally Indirect Prerequisite Eviction as a Retention Failure in Agentic Memory#656840arXiv (OAI Expanded)
• When Retrieval Fails Before It Begins: Structurally Indirect Prerequisite Eviction as a Retention Failure in Agentic Memory#658976arXiv (All)
• A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong#789767arXiv (OAI Expanded)
• A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong#793772arXiv (All)
• Symbolic Neural Generation with Applications to Lead Discovery in Drug Design#820269arXiv (All)
• Distributed ToA Localization of Acoustic Sources with Unknown Time of Emission via Operator Splitting#997091arXiv (All)
• Exact semantic readout from compressed vector representations#1011754arXiv (All)
• Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery#1013765arXiv (All)
• Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration#1035320arXiv (All)
• Multiple Nonlinear Waves by (Quantum) Neural Networks: Checking the AI supremacy#797724arXiv (OAI Expanded)
• Multiple Nonlinear Waves by (Quantum) Neural Networks: Checking the AI supremacy#799147arXiv (All)
• Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control#986925arXiv (All)
• Learning Hamiltonian Flow Maps from Numerical-Scheme Residuals for Long-Time Multiscale Simulation#664064arXiv (OAI Expanded)
• Learning Hamiltonian Flow Maps from Numerical-Scheme Residuals for Long-Time Multiscale Simulation#665564arXiv (All)
• A Unified Algebraic Framework for Classification Performance Evaluation#668603arXiv (OAI Expanded)
• A Unified Algebraic Framework for Classification Performance Evaluation#670668arXiv (All)
• Autoencoders in Function Space#799823arXiv (All)
• Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation#789116arXiv (OAI Expanded)
• Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation#793120arXiv (All)
• Divergence-Based Similarity Function for Multi-View Contrastive Learning#997979arXiv (All)
• Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer#921045arXiv (OAI Expanded)
• Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer#925281arXiv (All)
• Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct#1035575arXiv (All)
• JoLT: Joint Latent Trajectories for Context-Guided High-Resolution Tiled Generation#614395arXiv (OAI Expanded)
• JoLT: Joint Latent Trajectories for Context-Guided High-Resolution Tiled Generation#615362arXiv (All)
• JVLGS: Joint Vision-Language Gas Leak Segmentation#797222arXiv (OAI Expanded)
• JVLGS: Joint Vision-Language Gas Leak Segmentation#798635arXiv (All)
• But How Would AI Agents Run a Town's Economy?#998663arXiv (All)
• SAiFE-gym: Model-based Environments for Automated Market Making with Concentrated Liquidity#1011507arXiv (All)
• Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures#1012365arXiv (All)