2316 papers
This paper introduces efficient, representation-based transductive generalization bounds for graph node classification using optimal transport and Wasserstein distances, which not only correlate strongly with empirical performance but also explain the non-monotonic relationship between GNN depth and generalization error through the analysis of distributional transformations.
This paper introduces DendroNN, a novel dendrocentric neural network that leverages non-differentiable sequence detection and a rewiring phase to efficiently classify event-based spatiotemporal data, achieving competitive accuracy with up to 4x higher energy efficiency than state-of-the-art neuromorphic hardware through a dedicated asynchronous digital architecture.
This paper advances the theoretical understanding of Gaussian process Thompson sampling (GP-TS) in Bayesian optimization by establishing a regret lower bound, deriving improved upper bounds for cumulative regret and the second moment of regret, and providing expected lenient regret bounds that address gaps in existing analyses compared to GP-UCB.
This paper proposes a proxy-guided framework using variational autoencoders and causal modeling to identify and correct systematic measurement errors in aggregate outcome variables by leveraging proxy variables that depend on true outcomes but are independent of bias mechanisms.
This paper establishes a non-asymptotic Gaussian comparison theorem based on Gordon's theorem to rigorously validate dynamic mean-field expressions and derive refined iterative approximations for the training dynamics of machine learning models, such as perceptrons, under Gaussian mixture data.
The paper proposes CLoE, a consistency-driven framework that enhances missing-modality medical image segmentation by enforcing decision-level agreement among modality experts on both global and clinically critical foreground regions, thereby improving robustness and generalization compared to state-of-the-art methods.
The paper introduces Reward-Zero, a general-purpose implicit reward mechanism that leverages language embeddings to transform natural-language task descriptions into dense, semantically grounded progress signals, thereby accelerating training, stabilizing learning, and improving generalization for reinforcement learning agents without requiring task-specific reward engineering.
This paper introduces TA-GGAD, a testing-time adaptive graph foundation model that addresses the cross-domain generalization challenge in anomaly detection by identifying and modeling the "Anomaly Disassortativity" issue, thereby achieving state-of-the-art performance across diverse real-world graphs with a single training phase.
This paper presents a data-driven framework that combines a multilayer perceptron trained on experimental data augmented by a conditional generative adversarial network with an interactive 3D web interface to predict and visualize surface roughness in material extrusion additive manufacturing, enabling optimized process planning and part orientation.
This paper introduces a differentially private, zero-order optimization framework that extends dataset condensation to non-differentiable clinical models, enabling the creation of compact, privacy-preserving synthetic datasets that facilitate the democratization of clinical data sharing without compromising model utility.
The paper proposes CAHC, an end-to-end contrastive learning framework for attributed hypergraph clustering that integrates node-level and hyperedge-level objectives with joint embedding and cluster assignment optimization to outperform existing two-stage methods.
This paper proposes VSOPINN, a novel framework that integrates differentiable Voronoi tessellation with Physics-Informed Neural Networks to enable end-to-end optimization of sensor placement, thereby significantly enhancing the accuracy and robustness of high-fidelity flow field reconstruction under sparse measurements and sensor failures.
SPAARS is a curriculum learning framework for offline-to-online reinforcement learning that safely improves policies by initially exploring a low-dimensional latent space to ensure sample efficiency and stability, then seamlessly transitioning to raw action space to bypass decoder-induced performance ceilings, thereby achieving superior results over state-of-the-art baselines on both robotic manipulation and locomotion tasks.
This paper introduces the Fully Convolutional Diffusion Model (FCDM), a ConvNeXt-based architecture that achieves competitive generative performance with significantly fewer computational resources and training steps than Transformer-based counterparts, demonstrating that modern convolutional designs remain a highly efficient alternative for scaling diffusion models.
This paper proposes four enhancements to the Spatial-Temporal Matching algorithm—dynamic buffering, adaptive observation probability, a redesigned temporal scoring function, and behavioral analysis—to improve the efficiency and accuracy of reconstructing GPS trajectories from sparse, low-frequency data in dense urban environments, as validated by experiments in Milan.
This paper systematically analyzes how Markov Decision Process design choices impact the sim-to-real gap in industrial process control, demonstrating through a color mixing task that physics-based dynamics models significantly outperform simplified models in achieving real-world success under strict precision constraints.
This paper proposes Nonparametric Weighting (NW) and Model-assisted Nonparametric Weighting (MNW) estimators for off-policy evaluation in contextual bandits, which achieve lower variance than traditional Inverse Probability Weighting and Doubly Robust methods while maintaining low bias by constructing weights via nonparametric models and incorporating reward predictions.
This paper introduces Variational Mixture-of-Experts Routing (VMoER), a scalable Bayesian framework that confines uncertainty quantification to the expert-selection stage of Mixture-of-Experts Transformers, achieving significant improvements in calibration, stability, and out-of-distribution detection with negligible computational overhead.
This paper introduces temporal-conditioned normalizing flows (tcNF), a novel autoregressive framework that enhances multivariate time series anomaly detection by effectively modeling temporal dependencies and uncertainty to identify low-probability events with improved accuracy and robustness.
TrainDeeploy is a novel framework that enables efficient, parameter-efficient on-device fine-tuning of both CNN and Transformer models on ultra-low-power, memory-constrained RISC-V SoCs, achieving significant reductions in memory usage and computational overhead while supporting end-to-end training at the extreme edge.