i-2-6

Documents about i-2-6

• Neural Green's Operators for Parametric Partial Differential Equations#128288arXiv (OAI)
• LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios#128396arXiv (OAI)
• On Divergence Measures for Training GFlowNets#131253arXiv (OAI)
• Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight#131282arXiv (OAI)
• Dr. Jekyll and Mr. Hyde: Two Faces of LLMs#183092arXiv (OAI Expanded)
• A Survey on Vision-Language-Action Models for Embodied AI#189141arXiv (OAI Expanded)
• RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation#608962arXiv (OAI Expanded)
• Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion#609055arXiv (OAI Expanded)
• Wolff-Parkinson-White Detection at 471:1 Class Imbalance: A Leakage-Controlled Study of the Data Bottleneck#609071arXiv (OAI Expanded)
• Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs#609135arXiv (OAI Expanded)
• AccretionLink: On-Device Auditing of Exposure-Control Attacks on Attribute Inference#609168arXiv (OAI Expanded)
• Can Neural Networks Learn by Experimenting on Themselves? Self-Interventional Learning from Functional Consequences to Predictive Self-Knowledge#609311arXiv (OAI Expanded)
• Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs#609313arXiv (OAI Expanded)
• Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence#609320arXiv (OAI Expanded)
• RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation#610024arXiv (All)
• Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form#610976arXiv (OAI Expanded)
• Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form#612453arXiv (All)
• CytoNet: A Foundation Model for the Human Cerebral Cortex at Cellular Resolution#668353arXiv (OAI Expanded)
• Holographic Invariant Storage: Design-Time Safety Contracts via Vector Symbolic Architectures#668459arXiv (OAI Expanded)
• Output-Level Regularization Eliminates the Seed Lottery in Single-GPU VLA Fine-Tuning#668568arXiv (OAI Expanded)
• A Unified Algebraic Framework for Classification Performance Evaluation#668603arXiv (OAI Expanded)
• When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design#668649arXiv (OAI Expanded)
• Reproducible Evaluation of MoE Expert Caching: Replay Semantics, Workload Contamination, and Operating Regimes#668672arXiv (OAI Expanded)
• SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents#668674arXiv (OAI Expanded)
• What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs#674245arXiv (OAI Expanded)
• A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting#674369arXiv (OAI Expanded)
• A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad and Muon#674378arXiv (OAI Expanded)
• Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating#674489arXiv (OAI Expanded)
• What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs#677442arXiv (All)
• A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting#677568arXiv (All)
• A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad and Muon#677577arXiv (All)
• Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating#677690arXiv (All)
• The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior#684310arXiv (All)
• Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Making#684438arXiv (All)
• Learned Relay Representations for Forward-Thinking Discrete Diffusion Models#684464arXiv (All)
• Hypothesize, Evaluate, Refine: A Scientific Agent for PDE Discovery with Unknown Spatial Coefficient Fields#780793arXiv (All)

Related topics