deep-neural-networks

Documents about deep-neural-networks

• Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent#13076arXiv CS
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe#13077arXiv CS
• Loop Corrections to the Training and Generalization Errors of Random Feature Models#13090arXiv CS
• Algorithmic Analysis of Dense Associative Memory: Finite-Size Guarantees and Adversarial Robustness#13091arXiv CS
• VFA: Relieving Vector Operations in Flash Attention with Global Maximum Pre-computation#13094arXiv CS
• Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization#13096arXiv CS
• Data-driven Reachable Set Estimation with Tunable Adversarial and Wasserstein Distributional Guarantees#13107arXiv CS
• From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs#14003arXiv CS
• Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning#14018arXiv CS
• Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models#14021arXiv CS
• DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off#14032arXiv CS
• Simulation-Based Optimisation of Batting Order and Bowling Plans in T20 Cricket#14040arXiv CS
• UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization#14044arXiv CS
• Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate#14047arXiv CS
• RL-STPA: Adapting System-Theoretic Hazard Analysis for Safety-Critical Reinforcement Learning#19007arXiv CS
• Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning#19028arXiv CS
• STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing#19032arXiv CS
• Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task#19036arXiv CS
• Particle swarm optimization of deep neural networks architectures for image classification#19741Semantic Scholar
• Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case#19743Semantic Scholar
• EvoPruneDeepTL: An Evolutionary Pruning Model for Transfer Learning based Deep Neural Networks#19799Semantic Scholar
• Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization#31258arXiv CS
• Driving Assistance System for Ambulances to Minimise the Vibrations in Patient Cabin#31282arXiv CS
• Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning#31284arXiv CS
• (Weighted) Adaptive Radius Near Neighbor Search: Evaluation for WiFi Fingerprint-based Positioning#31295arXiv CS
• Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale#120496arXiv CS
• A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work#120503arXiv CS
• Barrier-enforced multi-objective optimization for direct point and sharp interval forecasting#120512arXiv CS
• Multi-Scale Reversible Chaos Game Representation: A Unified Framework for Sequence Classification#120516arXiv CS
• Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario#120524arXiv CS
• AutoPPA: Automated Circuit PPA Optimization via Contrastive Code-based Rule Library Learning#120525arXiv CS
• Balance-Guided Sparse Identification of Multiscale Nonlinear PDEs with Small-coefficient Terms#120530arXiv CS
• Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples#124034arXiv CS
• Physics-Conditioned Synthesis of Internal Ice-Layer Thickness for Incomplete Layer Traces#124041arXiv CS
• Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference#124043arXiv CS
• V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization#124046arXiv CS
• MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment#124057arXiv CS
• Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales#124058arXiv CS
• Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning#124062arXiv CS
• Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis#124068arXiv CS
• Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models#124076arXiv CS
• A Scale-Adaptive Framework for Joint Spatiotemporal Super-Resolution with Diffusion Models#126499arXiv CS
• On the algebra of Koopman eigenfunctions and on some of their infinities#126506arXiv CS
• Large-Scale Data Parallelization of Product Quantization and Inverted Indexing Using Dask#126526arXiv CS
• Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics#126542arXiv CS
• Decoding High-Dimensional Finger Motion from EMG Using Riemannian Features and RNNs#134555arXiv CS
• Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents#134561arXiv CS
• SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions#134573arXiv CS
• Personalized deep neural networks reveal mechanisms of math learning disabilities in children.#135955NCBI PubMed Central
• XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation#138924arXiv CS