neural-networks

Documents about neural-networks

• Safe Control using Learned Safety Filters and Adaptive Conformal Inference#120514arXiv CS
• NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization#120518arXiv CS
• Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference#120537arXiv CS
• Scale-free adaptive planning for deterministic dynamics & discounted rewards#120539arXiv CS
• Convergent Evolution: How Different Language Models Learn Similar Number Representations#124036arXiv CS
• Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity#124040arXiv CS
• Improving clinical interpretability of linear neuroimaging models through feature whitening#124059arXiv CS
• pAI/MSc: ML Theory Research with Humans on the Loop#124063arXiv CS
• Amortized Vine Copulas for High-Dimensional Density and Information Estimation#124069arXiv CS
• Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms#124075arXiv CS
• Interpretable facial dynamics as behavioral and perceptual traces of deepfakes#126513arXiv CS
• Dilated CNNs for Periodic Signal Processing: A Low-Complexity Approach#126525arXiv CS
• Geometric Characterisation and Structured Trajectory Surrogates for Clinical Dataset Condensation#126528arXiv CS
• Cross-Domain Data Selection and Augmentation for Automatic Compliance Detection#126539arXiv CS
• Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networks#131319arXiv (OAI)
• CLVAE: A Variational Autoencoder for Long-Term Customer Revenue Forecasting#134540arXiv CS
• The Exact Replica Threshold for Nonlinear Moments of Quantum States#134542arXiv CS
• Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs#134543arXiv CS
• Multi-output Extreme Spatial Model for Complex Aircraft Production Systems#134550arXiv CS
• On the Properties of Feature Attribution for Supervised Contrastive Learning#134551arXiv CS
• Towards Adaptive Continual Model Merging via Manifold-Aware Expert Evolution#134560arXiv CS
• SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning#138910arXiv CS
• SceneSelect: Selective Learning for Trajectory Scene Classification and Expert Scheduling#138937arXiv CS
• SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation#138950arXiv CS
• Diverse Image Priors for Black-box Data-free Knowledge Distillation#141479arXiv CS
• VAE-Inf: A statistically interpretable generative paradigm for imbalanced classification#141503arXiv CS
• QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention#141504arXiv CS
• RCProb: Probabilistic Rule Extraction for Efficient Simplification of Tree Ensembles#141505arXiv CS
• Online combinatorial optimization with stochastic decision sets and adversarial losses#141510arXiv CS
• Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models#146916arXiv CS
• Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing#146918arXiv CS
• DEFault++: Automated Fault Detection, Categorization, and Diagnosis for Transformer Architectures#146921arXiv CS
• MIFair: A Mutual-Information Framework for Intersectionality and Multiclass Fairness#146932arXiv CS
• FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning#146933arXiv CS
• Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications#146939arXiv CS
• Calibrating Attribution Proxies for Reward Allocation in Participatory Weather Sensing#146945arXiv CS
• Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing#146951arXiv CS
• CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting#146953arXiv CS
• Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation#151738arXiv CS
• Bridging Graph Drawing and Dimensionality Reduction with Stochastic Stress Optimization#151744arXiv CS
• Group Convolutional Neural Network for the Low-Energy Spectrum in the Quantum Dimer Model#128401arXiv (OAI)
• Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding#2581arXiv CS
• Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models#2582arXiv CS
• What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal#2583arXiv CS
• TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis#2589arXiv CS
• Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization#2597arXiv CS
• SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization#2600arXiv CS
• Scaling-Aware Data Selection for End-to-End Autonomous Driving Systems#2601arXiv CS
• Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation#2615arXiv CS
• A Direct Approach for Handling Contextual Bandits with Latent State Dynamics#2619arXiv CS