2403 papers
This paper reveals that pruning-based unlearning in diffusion models is inherently insecure because the locations of pruned weights act as side-channel signals that enable a novel, data-free, and training-free attack to fully revive erased concepts, prompting a call for safer pruning mechanisms that conceal these locations.
SR-TTT addresses the catastrophic recall failures of Test-Time Training (TTT) language models by introducing a loss-gated sparse memory mechanism that dynamically routes highly surprising tokens to an exact-attention residual cache, thereby preserving O(1) memory efficiency while enabling accurate retrieval of critical information.
This comprehensive review defines Quantum Deep Learning (QDL) through a four-paradigm taxonomy, critically assesses its theoretical foundations and experimental implementations across various hardware systems, and outlines a verification-aware roadmap for transitioning from near-term demonstrations to scalable, fault-tolerant applications.
This paper proposes a trust-aware federated learning framework that utilizes an Adaptive Trust Score Scaling and Filtering mechanism to secure bone healing stage interpretation in e-Health by mitigating the impact of unreliable or adversarial participants while maintaining model integrity and predictive performance.
The paper introduces HURRI-GAN, a novel TimeGAN-based framework that corrects systemic biases in high-resolution hurricane simulation models like ADCIRC, enabling accurate, near real-time storm surge forecasting and bias extrapolation beyond gauge station locations while significantly reducing computational runtime.
This paper introduces Geodesic Gradient Descent (GGD), a generic, learning-rate-free optimization algorithm that approximates local neighborhoods of objective function-induced hypersurfaces using n-dimensional spheres to ensure update trajectories remain on the manifold, achieving significant performance improvements over Adam on both regression and classification tasks.
This study demonstrates that the choice of graph construction technique significantly impacts IoT botnet detection performance, revealing that Gabriel graphs combined with Variational Autoencoders and Graph Attention Networks achieve the highest accuracy (97.56%) on the N-BaIoT dataset compared to other methods like k-NN and Shared Nearest Neighbor.
This paper introduces Projection-Augmented Graph (PAG), a novel Approximate Nearest Neighbor Search framework that integrates projection techniques into graph indexing to simultaneously achieve high query efficiency, fast indexing, low memory usage, and robust scalability across modern AI workloads, outperforming existing methods like HNSW by up to 5x in speed while supporting online insertions.
The paper introduces EnsAug, a novel training paradigm that improves human motion analysis by replacing the conventional single-model approach with an ensemble of specialists, each trained on data augmented by a distinct geometric transformation, thereby achieving state-of-the-art performance while respecting kinematic constraints.
The paper introduces HyperTokens, a transformer-based token generator augmented with meta-inspired regularizers and causal auxiliary supervision to enable efficient, low-forgetting continual Video-Language Understanding by dynamically producing task-specific prompts without increasing memory costs.
This paper introduces ERP-RiskBench, a leakage-safe ensemble learning framework for detecting financial risks in ERP systems that combines hybrid risk definitions, rigorous time- and group-aware validation to prevent data leakage, and a stacking gradient boosting model to deliver reproducible, interpretable, and operationally grounded fraud detection results.
This paper proposes an unsupervised CNN autoencoder with a novel weighted spectral angle distance loss to enable blind, automated unmixing of complex ATR-FTIR hyperspectral images from historical oil painting cross-sections, significantly improving the interpretability and scalability of material analysis compared to traditional manual methods.
This paper demonstrates that Graph Neural Networks outperform traditional models like TabNet in estimating muon particle momentum for the CMS experiment, highlighting the critical role of node feature dimensionality and the benefits of leveraging the data's inherent graph structure to improve trigger system efficiency.
This paper proposes a hybrid few-shot learning model integrating Siamese and Prototypical Networks with Grad-CAM-based Explainable AI to achieve high-accuracy, interpretable classification of maize, rice, and wheat leaf diseases under limited data conditions.
This paper addresses the limitations of current Large Vision-Language Models in deep chart research by proposing Parallel Relative Policy Optimization (PRPO) to resolve training conflicts and constructing the MCDR-Bench evaluation framework to enable objective assessment of complex reasoning capabilities.
This paper proposes a plug-and-play method called ABMS, which combines an additional backward denoising step with Monte-Carlo sampling to reduce estimation errors in posterior sampling and thereby improve the quality and consistency of training-free, loss-guided conditional generation across diverse tasks.
This paper presents an unsupervised learning framework utilizing convolutional filtering and neural networks with optimized early-stopping to achieve robust, high-fidelity reconstruction of ion-beam emittance images from noisy data, enabling unprecedented halo resolution beyond seven standard deviations for particle accelerator diagnostics.
This paper proposes Soft Equivariance Regularization (SER), a lightweight, plug-in method that decouples invariance and equivariance objectives by enforcing equivariance on intermediate spatial features while preserving invariance on the final embedding, thereby improving both linear evaluation accuracy and robustness to geometric perturbations without requiring auxiliary heads or transformation labels.
This paper argues that RGB-only Multimodal Large Language Models fail to generalize across different cameras due to entangled perspective and object properties, and proposes a Camera-Aware MLLM framework that integrates camera intrinsics, augmented data, and 3D geometric priors to achieve robust, generalizable spatial intelligence.
This paper enhances the reliability of solar flare regression by applying conformal prediction to deep learning models, demonstrating that conformalized quantile regression outperforms alternative methods in achieving valid coverage rates and favorable interval lengths for space weather forecasting.