deep-neural-networks

Documents about deep-neural-networks

• Aligning Flow Map Policies with Optimal Q-Guidance#178877arXiv CS
• From Message-Passing to Linearized Graph Sequence Models#178893arXiv CS
• SCNO: Spiking Compositional Neural Operator -- Towards a Neuromorphic Foundation Model for Nuclear PDE Solving#10347arXiv CS
• GlobalCY I: A JAX Framework for Globally Defined and Symmetry-Aware Neural Kähler Potentials#10377arXiv CS
• From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT#155312arXiv CS
• Automated Batch Distillation Process Simulation for a Large Hybrid Dataset for Deep Anomaly Detection#5990arXiv CS
• Event-Driven Temporal Graph Networks for Asynchronous Multi-Agent Cyber Defense in NetForge_RL#5947arXiv CS
• Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification#14020arXiv CS
• Stochastic-Dimension Frozen Sampled Neural Network for High-Dimensional Gross-Pitaevskii Equations on Unbounded Domains#5968arXiv CS
• Graph Neural Network based Hierarchy-Aware Embeddings of Knowledge Graphs: Applications to Yeast Phenotype Prediction#155311arXiv CS
• Drowsiness-Aware Adaptive Autonomous Braking System based on Deep Reinforcement Learning for Enhanced Road Safety#14037arXiv CS
• Differentially Private Language Generation and Identification in the Limit#2584arXiv CS
• QARIMA: A Quantum Approach To Classical Time Series Analysis#2610arXiv CS
• Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning#2617arXiv CS
• LINE: LLM-based Iterative Neuron Explanations for Vision Models#2628arXiv CS
• PhysInOne: Visual Physics Learning and Reasoning in One Suite#5960arXiv CS
• OASIS: Online Activation Subspace Learning for Memory-Efficient Training#5963arXiv CS
• Iterative Identification Closure: Amplifying Causal Identifiability in Linear SEMs#5974arXiv CS
• Beyond Segmentation: Structurally Informed Facade Parsing from Imperfect Images#5981arXiv CS
• Generalization and Scaling Laws for Mixture-of-Experts Transformers#5989arXiv CS
• Solving Physics Olympiad via Reinforcement Learning on Physics Simulators#10331arXiv CS
• Evaluating Cooperation in LLM Social Groups through Elected Leadership#10340arXiv CS
• Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration#10372arXiv CS
• CLAD: Efficient Log Anomaly Detection Directly on Compressed Representations#13075arXiv CS
• Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling#13092arXiv CS
• Analyzing the Effect of Noise in LLM Fine-tuning#13118arXiv CS
• Rhetorical Questions in LLM Representations: A Linear Probing Study#14004arXiv CS
• PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling#14023arXiv CS
• Gradient Descent's Last Iterate is Often (slightly) Suboptimal#14039arXiv CS
• Structural interpretability in SVMs with truncated orthogonal polynomial kernels#18996arXiv CS
• Cloning is as Hard as Learning for Stabilizer States#19000arXiv CS
• Context Over Content: Exposing Evaluation Faking in Automated Judges#19004arXiv CS
• Optimal algorithmic complexity of inference in quantum kernel methods#19006arXiv CS
• MambaSL: Exploring Single-Layer Mamba for Time Series Classification#19010arXiv CS
• LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking#19015arXiv CS
• MinShap: A Modified Shapley Value Approach for Feature Selection#19019arXiv CS
• Calibration-Gated LLM Pseudo-Observations for Online Contextual Bandits#19029arXiv CS
• The Whale Optimization Algorithm Approach for Deep Neural Networks#19740Semantic Scholar
• Surrogate optimization of deep neural networks for groundwater predictions#19764Semantic Scholar
• Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks#19773Semantic Scholar
• Learning to Reason with Insight for Informal Theorem Proving#31254arXiv CS
• Multi-Objective Bayesian Optimization via Adaptive \varepsilon-Constraints Decomposition#31292arXiv CS
• RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration#31294arXiv CS
• Enhancing Malware Detection by Fusing Static and Dynamic Features Using Deep Neural Networks#118510PhilArchive
• When Can LLMs Learn to Reason with Weak Supervision?#120495arXiv CS
• Deep neural networks optimization for resource-constrained environments: techniques and models#120631Semantic Scholar
• ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control#124037arXiv CS
• Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation#124045arXiv CS
• Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems#124047arXiv CS
• AAC: Admissible-by-Architecture Differentiable Landmark Compression for ALT#124048arXiv CS