deep-neural-networks

Documents about deep-neural-networks

• Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers#175246arXiv CS
• The Generalized Turing Test: A Foundation for Comparing Intelligence#175256arXiv CS
• Conditional anomaly detection methods for patient-management alert systems#175257arXiv CS
• NoRIN: Backbone-Adaptive Reversible Normalization for Time-Series Forecasting#175262arXiv CS
• Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation#178859arXiv CS
• Task-Adaptive Embedding Refinement via Test-time LLM Guidance#178861arXiv CS
• Learning, Fast and Slow: Towards LLMs That Adapt Continually#178862arXiv CS
• Solve the Loop: Attractor Models for Language and Reasoning#178867arXiv CS
• A proximal gradient algorithm for composite log-concave sampling#178871arXiv CS
• Scalable Token-Level Hallucination Detection in Large Language Models#178887arXiv CS
• Discrete Flow Matching for Offline-to-Online Reinforcement Learning#178889arXiv CS
• Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts#178890arXiv CS
• Residual-loss Anomaly Analysis of Physics-Informed Neural Networks: An Inverse Method for Change-point Detection in Nonlinear Dynamical Systems with Regime Switching#141485arXiv CS
• 3D CAD Models Reconstruction from 2D Drawings: A Survey and Future Challenges#7909HAL (France)
• The Impact of Dimensionality on the Stability of Node Embeddings#2585arXiv CS
• Provably Adaptive Linear Approximation for the Shapley Value and Beyond#2592arXiv CS
• On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities#2594arXiv CS
• What a Comfortable World: Ergonomic Principles Guided Apartment Layout Generation#2596arXiv CS
• Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models#2606arXiv CS
• An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations#2611arXiv CS
• Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings#2614arXiv CS
• Continuous Orthogonal Mode Decomposition: Haptic Signal Prediction in Tactile Internet#5955arXiv CS
• Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer#5961arXiv CS
• Hierarchical Flow Decomposition for Turning Movement Prediction at Signalized Intersections#5971arXiv CS
• Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima#5982arXiv CS
• MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI#10335arXiv CS
• Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions#10338arXiv CS
• Universality of first-order methods on random and deterministic matrices#10339arXiv CS
• Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning#10341arXiv CS
• Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data#13079arXiv CS
• GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees#13097arXiv CS
• RPRA: Predicting an LLM-Judge for Efficient but Performant Inference#13109arXiv CS
• EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts#13113arXiv CS
• Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems#13115arXiv CS
• Momentum Further Constrains Sharpness at the Edge of Stochastic Stability#14007arXiv CS
• Evaluating Supervised Machine Learning Models: Principles, Pitfalls, and Metric Selection#14036arXiv CS
• SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention#14041arXiv CS
• Beyond State Consistency: Behavior Consistency in Text-Based World Models#14043arXiv CS
• Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations#18994arXiv CS
• Class Unlearning via Depth-Aware Removal of Forget-Specific Directions#19014arXiv CS
• Metric-agnostic Learning-to-Rank via Boosting and Rank Approximation#19020arXiv CS
• LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning#19034arXiv CS
• A survey of the recent architectures of deep convolutional neural networks#19729Semantic Scholar
• Revisiting Approximate Metric Optimization in the Age of Deep Neural Networks#19754Semantic Scholar
• Information Router for Mitigating Modality Dominance in Vision-Language Models#31256arXiv CS
• Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction#31261arXiv CS
• OT on the Map: Quantifying Domain Shifts in Geographic Space#31263arXiv CS
• JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models#31266arXiv CS
• Tabular foundation models for in-context prediction of molecular properties#31269arXiv CS
• Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance#31274arXiv CS