deep-neural-networks

Documents about deep-neural-networks

• ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection#14030arXiv CS
• MolCryst-MLIPs: A Machine-Learned Interatomic Potentials Database for Molecular Crystals#14033arXiv CS
• Generalization in LLM Problem Solving: The Case of the Shortest Path#18993arXiv CS
• When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence#19013arXiv CS
• IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation#19018arXiv CS
• Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography#19021arXiv CS
• DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models#19025arXiv CS
• Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching#19027arXiv CS
• Multi-User mmWave Beam and Rate Adaptation via Combinatorial Satisficing Bandits#19035arXiv CS
• Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization#19727Semantic Scholar
• Molecular optimization by capturing chemist’s intuition using deep neural networks#19760Semantic Scholar
• Fixed-point optimization of deep neural networks with adaptive step size retraining#19768Semantic Scholar
• Quantization and Deployment of Deep Neural Networks on Microcontrollers#19802Semantic Scholar
• Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model#31272arXiv CS
• Evaluating quality in synthetic data generation for large tabular health datasets#31291arXiv CS
• Understanding by Analogy? On the Potential Role of Complexity Science in Explaining Deep Neural Networks#107869PhilArchive
• Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk#120506arXiv CS
• Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts#120517arXiv CS
• Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation#120519arXiv CS
• Using large language models for embodied planning introduces systematic safety risks#120522arXiv CS
• Predictive Modeling of Natural Medicinal Compounds for Alzheimer Disease Using Cheminformatics#120538arXiv CS
• LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image#124038arXiv CS
• Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees#124074arXiv CS
• Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability#126494arXiv CS
• Probably Approximately Consensus: On the Learning Theory of Finding Common Ground#126507arXiv CS
• Fixation Sequences as Time Series: A Topological Approach to Dyslexia Detection#126518arXiv CS
• A-IC3: Learning-Guided Adaptive Inductive Generalization for Hardware Model Checking#126522arXiv CS
• Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions#126523arXiv CS
• Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation#126527arXiv CS
• Time-Localized Parametric Decomposition of Respiratory Airflow for Sub-Breath Analysis#134534arXiv CS
• Are Natural-Domain Foundation Models Effective for Accelerated Cardiac MRI Reconstruction?#134549arXiv CS
• Different Strokes for Different Folks: Writer Identification for Historical Arabic Manuscripts#134554arXiv CS
• HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models#134562arXiv CS
• Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control#134565arXiv CS
• Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models#134566arXiv CS
• Pack only the essentials: Adaptive dictionary learning for kernel ridge regression#134570arXiv CS
• Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling#138911arXiv CS
• Diffusion-Guided Feature Selection via Nishimori Temperature: Noise-Based Spectral Embedding#138915arXiv CS
• The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications#138918arXiv CS
• Efficient learning by implicit exploration in bandit problems with side observations#138929arXiv CS
• GradMAP: Gradient-Based Multi-Agent Proximal Learning for Grid-Edge Flexibility#138931arXiv CS
• Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models#141468arXiv CS
• TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning#141470arXiv CS
• Barriers to Universal Reasoning With Transformers (And How to Overcome Them)#141477arXiv CS
• Measuring the Sensitivity of Classification Models with the Error Sensitivity Profile#141481arXiv CS
• Enhancing SignSGD: Small-Batch Convergence Analysis and a Hybrid Switching Strategy#141492arXiv CS
• Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models#141499arXiv CS
• Mapping the Phase Diagram of the Vicsek Model with Machine Learning#146913arXiv CS
• Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces#146919arXiv CS
• Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression#146922arXiv CS