i-2-6

Documents about i-2-6

• Prediction emerges in RNNs trained for perception#924875arXiv (All)
• BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice#788892arXiv (OAI Expanded)
• BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice#792896arXiv (All)
• How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework#820464arXiv (All)
• MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models#927566arXiv (All)
• CMRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments#973173arXiv (All)
• Definitional Sensitivity in Media Bias Detection: A Multi-Definition Dataset and Benchmark#984230arXiv (All)
• Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal#996793arXiv (All)
• Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits#1011268arXiv (All)
• Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior#618925arXiv (OAI Expanded)
• Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior#620604arXiv (All)
• PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations#985320arXiv (All)
• A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification#820559arXiv (All)
• SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context#999276arXiv (All)
• Transfer Learning of Keystroke Dynamics for Cross-Device User Authentication#619055arXiv (OAI Expanded)
• Transfer Learning of Keystroke Dynamics for Cross-Device User Authentication#620734arXiv (All)
• Iterative Exploration-Driven Sparse SDP Clustering via Thompson Sampling#1010999arXiv (All)
• Transformation Laws in Neural Representations: Structure, Realisability, and Construction#1011884arXiv (All)
• Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems#809501arXiv (OAI Expanded)
• Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems#819497arXiv (All)
• FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion#613991arXiv (OAI Expanded)
• FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion#614958arXiv (All)
• Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks#633605arXiv (OAI Expanded)
• Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks#635954arXiv (All)
• Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula#797852arXiv (OAI Expanded)
• Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula#799275arXiv (All)
• CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards#975238arXiv (All)
• IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies#998490arXiv (All)
• Federated Soft Clustering via Generalized Total Variation Minimization#1013802arXiv (All)
• The Manifold Hypothesis under Unknown Gaussian Noise:Conditional Certificates and Consistent Dimension Estimation#1035718arXiv (All)
• Clustering-Based Collective Anomaly Detection in IoT Systems: A Graph Neural Network Approach#1036849arXiv (All)
• CleanScore: Black-Box Benchmark Audits with Negative Controls and Sensitivity Bounds#1036866arXiv (All)
• Distributed Linear Solvers and Data Heterogeneity#1037652arXiv (All)
• RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis#822159arXiv (All)
• A Dynamic Fusion Large Language Model for Traffic Flow Prediction#998851arXiv (All)
• 2 U.S.C. § 31b-6 — Repealed. Pub. L. 99–151, title I, § 102(b), Nov. 13, 1985, 99 Stat. 797#558962US Code (LII)
• Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models#633544arXiv (OAI Expanded)
• Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models#635893arXiv (All)
• EdgeReMIND: A Scalable, Top-Ranked Memorization Baseline for Temporal Multi-Relational Link Prediction#1011630arXiv (All)
• Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets#618686arXiv (OAI Expanded)
• Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets#620365arXiv (All)
• Action-grounded tissue affordance enables anticipatory auto-framing that lowers surgeon cognitive workload during laparoscopic surgery#661414arXiv (OAI Expanded)
• Action-grounded tissue affordance enables anticipatory auto-framing that lowers surgeon cognitive workload during laparoscopic surgery#662464arXiv (All)
• Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems#1035457arXiv (All)
• Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion#609055arXiv (OAI Expanded)
• Toward Better Assessment of LLMs' Performance in Clinical Error Detection#622941arXiv (OAI Expanded)
• Toward Better Assessment of LLMs' Performance in Clinical Error Detection#625214arXiv (All)
• The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior#682535arXiv (OAI Expanded)
• The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior#684310arXiv (All)
• Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification#789834arXiv (OAI Expanded)