neural-networks

Documents about neural-networks

• StructMem: Structured Memory for Long-Horizon Behavior in LLMs#126515arXiv CS
• Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks#126519arXiv CS
• There Will Be a Scientific Theory of Deep Learning#126520arXiv CS
• Dynamical Priors as a Training Objective in Reinforcement Learning#126540arXiv CS
• Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation#126585arXiv CS
• Optimizing Biophysical Large-Scale Brain Circuit Models With Deep Neural Networks#131009bioRxiv / medRxiv
• SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning#134548arXiv CS
• Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples#134558arXiv CS
• Statistical retrieval of atmospheric profiles with deep convolutional neural networks#137349HAL (France)
• The Optimal Sample Complexity of Multiclass and List Learning#138907arXiv CS
• Conflict-Aware Harmonized Rotational Gradient for Multiscale Kinetic Regimes#138908arXiv CS
• Energy-Arena: A Dynamic Benchmark for Operational Energy Forecasting#138914arXiv CS
• Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction#138916arXiv CS
• The Last Human-Written Paper: Agent-Native Research Artifacts#138920arXiv CS
• Computational Design and Experimental Validation of Photoactive PARP1 Inhibitors#138922arXiv CS
• Meta-CoT: Enhancing Granularity and Generalization in Image Editing#138923arXiv CS
• A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning#138935arXiv CS
• An Automatic Ground Collision Avoidance System with Reinforcement Learning#138945arXiv CS
• Toward a Functional Geometric Algebra for Natural Language Semantics#141469arXiv CS
• G-Loss: Graph-Guided Fine-Tuning of Language Models#141475arXiv CS
• Improving Diversity in Black-box Few-shot Knowledge Distillation#141478arXiv CS
• Emergent Self-Attention from Astrocyte-Gated Associative Memory Dynamics#141496arXiv CS
• Subspace Optimization for Efficient Federated Learning under Heterogeneous Data#141497arXiv CS
• Exploration Hacking: Can LLMs Learn to Resist RL Training?#146907arXiv CS
• Synthetic Computers at Scale for Long-Horizon Productivity Simulation#146908arXiv CS
• Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders#146910arXiv CS
• Strait: Perceiving Priority and Interference in ML Inference Serving#146911arXiv CS
• Sequential Inference for Gaussian Processes: A Signal Processing Perspective#146914arXiv CS
• A Unified Framework of Hyperbolic Graph Representation Learning Methods#146926arXiv CS
• Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification#146935arXiv CS
• Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning#146937arXiv CS
• Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning#146938arXiv CS
• Diffusion-OAMP for Joint Image Compression and Wireless Transmission#146943arXiv CS
• In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks#146950arXiv CS
• HyCOP: Hybrid Composition Operators for Interpretable Learning of PDEs#151714arXiv CS
• RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution#151716arXiv CS
• EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure#151728arXiv CS
• Dermatologist-level classification of skin cancer with deep neural networks#6461OpenAlex
• Training the parametric interactions in an analog bosonic quantum neural network with Fock basis measurement#141675arXiv (OAI)
• Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks#20382DOAJ
• Physics informed and data-based augmented learning in structural health diagnosis#8250HAL (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
• Topology-aware design of spiking neural networks via modular graph architectures.#3703NCBI PubMed Central
• Continuous Orthogonal Mode Decomposition: Haptic Signal Prediction in Tactile Internet#5955arXiv CS