deep-neural-networks

Documents about deep-neural-networks

• D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery#146941arXiv CS
• Differentiable latent structure discovery for interpretable forecasting in clinical time series#146942arXiv CS
• Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values#151720arXiv CS
• NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search#151723arXiv CS
• Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning#151736arXiv CS
• BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis#151748arXiv CS
• SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters#151760arXiv CS
• Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs#155276arXiv CS
• Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM#155278arXiv CS
• Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes#155281arXiv CS
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration#155295arXiv CS
• The Manokhin Probability Matrix: A Diagnostic Framework for Classifier Probability Quality#155296arXiv CS
• Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers#155301arXiv CS
• Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs#155313arXiv CS
• Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe#155314arXiv CS
• Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models#168307arXiv CS
• Hybrid Quantum-Classical GANs for the Generation of Adversarial Network Flows#168310arXiv CS
• Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent#168317arXiv CS
• UniSD: Towards a Unified Self-Distillation Framework for Large Language Models#168321arXiv CS
• RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards#175247arXiv CS
• AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents#175252arXiv CS
• Factual recall in linear associative memories: sharp asymptotics and mechanistic insights#175272arXiv CS
• MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization#175276arXiv CS
• AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery#175284arXiv CS
• KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference#178866arXiv CS
• ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models#178873arXiv CS
• ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging#178876arXiv CS
• Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space#178878arXiv CS
• SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation#178884arXiv CS
• Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning#178885arXiv CS
• Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds#178902arXiv CS
• R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow#180638arXiv CS
• Statistical Properties of the King Wen Sequence: An Anti-Habituation Structure That Does Not Improve Neural Network Training#5984arXiv CS
• On the Role of DAG topology in Energy-Aware Cloud Scheduling : A GNN-Based Deep Reinforcement Learning Approach#5986arXiv CS
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks#6189OpenAlex
• Spatiotemporal Convolutions on EEG signal -- A Representation Learning Perspective on Efficient and Explainable EEG Classification with Convolutional Neural Nets#155288arXiv CS
• SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions#2586arXiv CS
• A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation#2590arXiv CS
• Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers#2605arXiv CS
• Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?#2623arXiv CS
• MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs#5935arXiv CS
• RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval#5950arXiv CS
• ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion#5954arXiv CS
• Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories#5957arXiv CS
• Bringing Clustering to MLL: Weakly-Supervised Clustering for Partial Multi-Label Learning#5969arXiv CS
• Minimizing classical resources in variational measurement-based quantum computation for generative modeling#10352arXiv CS
• Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference#10366arXiv CS
• Structural Consequences of Policy-Based Interventions on the Global Supply Chain Network#10369arXiv CS
• Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books#10373arXiv CS
• Active Bayesian Inference for Robust Control under Sensor False Data Injection Attacks#10376arXiv CS