deep-neural-networks

Documents about deep-neural-networks

• Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts#151750arXiv CS
• Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance#151755arXiv CS
• Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots#151756arXiv CS
• Tempus: A Temporally Scalable Resource-Invariant GEMM Streaming Framework for Versal AI Edge#151758arXiv CS
• Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems#151763arXiv CS
• A Closed-Form Adaptive-Landmark Kernel for Certified Point-Cloud and Graph Classification#155269arXiv CS
• Graph Convolutional Support Vector Regression for Robust Spatiotemporal Forecasting of Urban Air Pollution#155299arXiv CS
• Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification#155310arXiv CS
• Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking#158567arXiv CS
• Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less#168301arXiv CS
• When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels#168302arXiv CS
• The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity#168315arXiv CS
• How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation#168319arXiv CS
• Optimal Counterfactual Search in Tree Ensembles: A Study Across Modeling and Solution Paradigms#168335arXiv CS
• Uncovering advanced transfer learning strategies for deep neural networks in natural language processing.#171978NCBI PubMed Central
• DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices#175239arXiv CS
• V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction#175248arXiv CS
• SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing#175260arXiv CS
• Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models#175282arXiv CS
• Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs#175283arXiv CS
• Deep Learning Based Depression Detection Using MRI Brain Scans#68168Zenodo (CERN)
• An Integrated Deep-Learning Framework for Peptide-Protein Interaction Prediction and Target-Conditioned Peptide Generation with ConGA-PePPI and TC-PepGen#120520arXiv CS
• Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training#2603arXiv CS
• OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation#2624arXiv CS
• Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies#5987arXiv CS
• Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems#10330arXiv CS
• KL Divergence Between Gaussians: A Step-by-Step Derivation for the Variational Autoencoder Objective#10337arXiv CS
• Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind#10343arXiv CS
• Computation of Least Trimmed Squares: A Branch-and-Bound framework with Hyperplane Arrangement Enhancements#10350arXiv CS
• Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach#10356arXiv CS
• Machine-learning modeling of magnetization dynamics in quasi-equilibrium and driven metallic spin systems#10360arXiv CS
• Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization#10362arXiv CS
• Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers#10363arXiv CS
• Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation#13078arXiv CS
• Frequency-aware Decomposition Learning for Sensorless Wrench Forecasting on a Vibration-rich Hydraulic Manipulator#13086arXiv CS
• Do VLMs Truly "Read" Candlesticks? A Multi-Scale Benchmark for Visual Stock Price Forecasting#13105arXiv CS
• From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space#14001arXiv CS
• ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation#14006arXiv CS
• A Comparative Study of Dynamic Programming and Reinforcement Learning in Finite Horizon Dynamic Pricing#14011arXiv CS
• First-See-Then-Design: A Multi-Stakeholder View for Optimal Performance-Fairness Trade-Offs#14014arXiv CS
• Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study#14029arXiv CS
• Driving Engagement in Daily Fantasy Sports with a Scalable and Urgency-Aware Ranking Engine#14049arXiv CS
• SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation#18999arXiv CS
• Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier#19002arXiv CS
• An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation#19011arXiv CS
• When Fairness Metrics Disagree: Evaluating the Reliability of Demographic Fairness Assessment in Machine Learning#19024arXiv CS
• Constant-Factor Approximations for Doubly Constrained Fair k-Center, k-Median and k-Means#31280arXiv CS
• Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures#31283arXiv CS
• A multimodal and temporal foundation model for virtual patient representations at healthcare system scale#120497arXiv CS
• Benchmarking System Dynamics AI Assistants: Cloud Versus Local LLMs on CLD Extraction and Discussion#120500arXiv CS