deep-neural-networks

Documents about deep-neural-networks

• Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks#5962arXiv CS
• Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI#138939arXiv CS
• Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty#141471arXiv CS
• BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation#168325arXiv CS
• bacpipe: a Python package to make bioacoustic deep learning models accessible#10354arXiv CS
• Deep Learning for Model Calibration in Simulation of Itaconic Acid Production#134556arXiv CS
• Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks#2598arXiv CS
• Hardware-Efficient Neuro-Symbolic Networks with the Exp-Minus-Log Operator#14038arXiv CS
• GFlowState: Visualizing the Training of Generative Flow Networks Beyond the Reward#126505arXiv CS
• Drug Synergy Prediction via Residual Graph Isomorphism Networks and Attention Mechanisms#126538arXiv CS
• Synthetic Data for any Differentiable Target#2595arXiv CS
• DMax: Aggressive Parallel Decoding for dLLMs#2609arXiv CS
• Long-Term Embeddings for Balanced Personalization#2616arXiv CS
• Multimodal Latent Reasoning via Predictive Embeddings#2626arXiv CS
• Stability Enhanced Gaussian Process Variational Autoencoders#5972arXiv CS
• ADD for Multi-Bit Image Watermarking#10367arXiv CS
• Agentic Control in Variational Language Models#13116arXiv CS
• Diffusion Language Models for Speech Recognition#14019arXiv CS
• Sandpile Economics: Theory, Identification, and Evidence#14034arXiv CS
• Prism: Symbolic Superoptimization of Tensor Programs#18998arXiv CS
• Stability and Generalization in Looped Transformers#19001arXiv CS
• AdaSplash-2: Faster Differentiable Sparse Attention#19009arXiv CS
• Amortized Optimal Transport from Sliced Potentials#19017arXiv CS
• Improving Sparse Autoencoder with Dynamic Attention#19033arXiv CS
• Duality for the Adversarial Total Variation#120507arXiv CS
• Spectral bandits for smooth graph functions#120528arXiv CS
• A weighted angle distance on strings#124061arXiv CS
• Fairness under uncertainty in sequential decisions#126517arXiv CS
• Associativity-Peakiness Metric for Contingency Tables#134538arXiv CS
• Learning to Think from Multiple Thinkers#138909arXiv CS
• Do Sparse Autoencoders Capture Concept Manifolds?#146920arXiv CS
• Decentralized Proximal Stochastic Gradient Langevin Dynamics#151730arXiv CS
• Adaptive Querying with AI Persona Priors#151734arXiv CS
• Unlearning Offline Stochastic Multi-Armed Bandits#151746arXiv CS
• On Adaptivity in Zeroth-Order Optimization#155289arXiv CS
• Predicting missing values: A good idea?#155306arXiv CS
• Free Decompression with Algebraic Spectral Curves#155318arXiv CS
• Towards Certified Unlearning for Deep Neural Networks#158636arXiv (OAI)
• Inductive Venn-Abers and related regressors#168304arXiv CS
• Optimizing Social Utility in Sequential Experiments#168344arXiv CS
• Benchmarking Sensor-Fault Robustness in Forecasting#175263arXiv CS
• Search Your Block Floating Point Scales!#178869arXiv CS
• Dermatologist-level classification of skin cancer with deep neural networks#6461OpenAlex
• Neural Recovery of Historical Lexical Structure in Bantu Languages from Modern Data#134531arXiv CS
• Neural Aided Kalman Filtering for UAV State Estimation in Degraded Sensing Environments#146923arXiv CS
• SNAPO: Smooth Neural Adjoint Policy Optimization for Optimal Control via Differentiable Simulation#168331arXiv CS
• An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling#124066arXiv CS
• nuGAN: Generative Adversarial Emulator for Cosmic Web with Neutrinos#168804Digital Commons @ Michigan Tech
• Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers#10364arXiv CS
• Early Detection of Acute Myeloid Leukemia (AML) Using YOLOv12 Deep Learning Model#31276arXiv CS