deep-neural-networks

Documents about deep-neural-networks

• UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models#120509arXiv CS
• Semantic Step Prediction: Multi-Step Latent Forecasting in LLM Reasoning Trajectories via Step Sampling#120521arXiv CS
• Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes#120533arXiv CS
• Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning#120534arXiv CS
• Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems#120536arXiv CS
• Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series#124035arXiv CS
• Personalized electric vehicle energy consumption estimation framework that integrates driver behavior with map data#124044arXiv CS
• F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel#124049arXiv CS
• Fast Bayesian equipment condition monitoring via simulation based inference: applications to heat exchanger health#124050arXiv CS
• GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning#124060arXiv CS
• MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation#124077arXiv CS
• On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification#126530arXiv CS
• Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings#134537arXiv CS
• SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference#134547arXiv CS
• Dual Control of Linear Systems from Bilinear Observations with Belief Space Model Predictive Control#138919arXiv CS
• Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics#141467arXiv CS
• From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling#141476arXiv CS
• From Cursed to Competitive: Closing the ZO-FO Gap via Input-to-State Stability#141501arXiv CS
• Optimization-Free Topological Sort for Causal Discovery via the Schur Complement of Score Jacobians#141506arXiv CS
• DGLight: DQN-Guided GRPO Fine-Tuning of Large Language Models for Traffic Signal Control#141511arXiv CS
• Assessing the Role of Intersection Proximity in Pedestrian Crashes: Insights from Data Mining Approach#146927arXiv CS
• Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game#151735arXiv CS
• AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments#151739arXiv CS
• Vesselpose: Vessel Graph Reconstruction from Learned Voxel-wise Direction Vectors in 3D Vascular Images#151757arXiv CS
• Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning#155275arXiv CS
• Weight-Decay Turns Transformer Loss Landscapes Villani: Functional-Analytic Foundations for Optimization and Generalization#168320arXiv CS
• DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency#168324arXiv CS
• PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization#168328arXiv CS
• Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models#168343arXiv CS
• Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training#175259arXiv CS
• The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies#175270arXiv CS
• On the global convergence of gradient descent for wide shallow models with bounded nonlinearities#175279arXiv CS
• Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts#178865arXiv CS
• Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs#178872arXiv CS
• OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning#178881arXiv CS
• Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training#178888arXiv CS
• EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment#2604arXiv CS
• HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology#2608arXiv CS
• Approximation of the Basset force in the Maxey-Riley-Gatignol equations via universal differential equations#2613arXiv CS
• Is More Data Worth the Cost? Dataset Scaling Laws in a Tiny Attention-Only Decoder#5965arXiv CS
• Drift-Aware Online Dynamic Learning for Nonstationary Multivariate Time Series: Application to Sintering Quality Prediction#5970arXiv CS
• DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings#5983arXiv CS
• Legal2LogicICL: Improving Generalization in Transforming Legal Cases to Logical Formulas via Diverse Few-Shot Learning#10342arXiv CS
• Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning#14048arXiv CS
• What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers#19026arXiv CS
• Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks#19761Semantic Scholar
• smart task#27620DataCite
• smart task#27621DataCite
• Corner Reflector Array Jamming Discrimination Using Multi-Dimensional Micro-Motion Features with Frequency Agile Radar#31288arXiv CS
• Impact of Nonlinear Power Amplifier on Massive MIMO: Machine Learning Prediction Under Realistic Radio Channel#31289arXiv CS