deep-neural-networks

Documents about deep-neural-networks

• Hybrid Deep Learning Approach for Coupled Demand Forecasting and Supply Chain Optimization#126535arXiv CS
• Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks#5951arXiv CS
• Generative Flow Networks for Model Adaptation in Digital Twins of Natural Systems#124055arXiv CS
• Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks#138921arXiv CS
• ControBench: An Interaction-Aware Benchmark for Controversial Discourse Analysis on Social Networks#151762arXiv CS
• KV Cache Offloading for Context-Intensive Tasks#2593arXiv CS
• Automating aggregation strategy selection in federated learning#2627arXiv CS
• Integrated electro-optic attention nonlinearities for transformers#5949arXiv CS
• Offline Local Search for Online Stochastic Bandits#5958arXiv CS
• Efficient Unlearning through Maximizing Relearning Convergence Delay#5964arXiv CS
• Online Intention Prediction via Control-Informed Learning#5975arXiv CS
• MixFlow: Mixed Source Distributions Improve Rectified Flows#5988arXiv CS
• Autonomous Diffractometry Enabled by Visual Reinforcement Learning#10334arXiv CS
• Towards Autonomous Mechanistic Reasoning in Virtual Cells#10344arXiv CS
• Calibration-Aware Policy Optimization for Reasoning LLMs#13110arXiv CS
• Adaptive Budget Allocation in LLM-Augmented Surveys#13117arXiv CS
• TIP: Token Importance in On-Policy Distillation#14008arXiv CS
• Context Sensitivity Improves Human-Machine Visual Alignment#14035arXiv CS
• RPS: Information Elicitation with Reinforcement Prompt Selection#14045arXiv CS
• Composite Silhouette: A Subsampling-based Aggregation Strategy#14046arXiv CS
• Unsupervised feature selection using Bayesian Tucker decomposition#19030arXiv CS
• Beyond Importance Sampling: Rejection-Gated Policy Optimization#19038arXiv CS
• An Efficient Optimization Technique for Training Deep Neural Networks#19721Semantic Scholar
• Synthetic data in cryptocurrencies using generative models#31265arXiv CS
• A Wasserstein Geometric Framework for Hebbian Plasticity#31281arXiv CS
• Discovering quantum phenomena with Interpretable Machine Learning#31287arXiv CS
• Revisiting Active Sequential Prediction-Powered Mean Estimation#120498arXiv CS
• ConforNets: Latents-Based Conformational Control in OpenFold3#120501arXiv CS
• FUSE: Ensembling Verifiers with Zero Labeled Data#120505arXiv CS
• IDOBE: Infectious Disease Outbreak forecasting Benchmark Ecosystem#120508arXiv CS
• Symmetry Guarantees Statistic Recovery in Variational Inference#120540arXiv CS
• Efficient Symbolic Computations for Identifying Causal Effects#124071arXiv CS
• Explicit Dropout: Deterministic Regularization for Transformer Architectures#124073arXiv CS
• Low-Rank Adaptation Redux for Large Models#126498arXiv CS
• Compliance Moral Hazard and the Backfiring Mandate#126510arXiv CS
• Verifying Machine Learning Interpretability Requirements through Provenance#126531arXiv CS
• Conditional anomaly detection with soft harmonic functions#126541arXiv CS
• Exponential families from a single KL identity#146930arXiv CS
• Geometry-Calibrated Conformal Abstention for Language Models#146947arXiv CS
• Prediction-powered Inference by Mixture of Experts#146949arXiv CS
• Make Your LVLM KV Cache More Lightweight#151717arXiv CS
• Aitchison Embeddings for Learning Compositional Graph Representations#151731arXiv CS
• Class Angular Distortion Index for Dimensionality Reduction#151747arXiv CS
• Transformers with Selective Access to Early Representations#155277arXiv CS
• PHALAR: Phasors for Learned Musical Audio Representations#155280arXiv CS
• Memory-Efficient Continual Learning with CLIP Models#155290arXiv CS
• Realizable Bayes-Consistency for General Metric Losses#155294arXiv CS
• Low Rank Tensor Completion via Adaptive ADMM#155305arXiv CS
• PianoCoRe: Combined and Refined Piano MIDI Dataset#168312arXiv CS
• On the Safety of Graph Representation Learning#168329arXiv CS