4882 papers
This paper proposes efficient data reduction strategies for semi-supervised adversarial training that utilize latent clustering techniques to select or generate critical boundary-adjacent samples, significantly reducing data requirements and computational costs while maintaining state-of-the-art robustness.
This paper derives error bounds for the excess risk of deep neural network classifiers trained on noisy labels by decomposing the risk into statistical and approximation errors, utilizing independent block construction for dependent data and refining results under the low-dimensional manifold hypothesis.
This paper introduces Generative Predictive Control (GPC), a framework that enhances robotic manipulation by combining a diffusion-based policy with an action-conditioned world model to enable online planning and optimization, consistently outperforming standard behavior cloning across diverse simulation and real-world tasks.
This paper theoretically demonstrates that in distributed computing systems with probabilistic stragglers, the approximation errors of Berrut Approximate Coded Computing (BACC) and Learning Theoretic Coded Computing (LeTCC) schemes converge to zero at specific rates despite the average number of stragglers scaling with the total server count, a finding validated through experiments on various functions including deep neural networks.
This paper introduces GRADIEND, a novel encoder-decoder method that utilizes model gradients to identify and rewrite specific neural network weights, effectively debiasing AI systems regarding gender, race, and religion while preserving their other capabilities.
This paper evaluates the security and quality of code generated by Large Language Models across multiple programming languages using a 200-task dataset, revealing that while LLMs can automate coding, they often fail to adopt modern security features and rely on outdated practices, particularly in languages like C++ and Java 17.
This paper proposes a novel local search algorithm with a balanced optimization objective and provable linear convergence to efficiently identify polarized communities in signed networks, effectively addressing size imbalance and scaling to large datasets while outperforming state-of-the-art methods.
This paper introduces CLEF, a controllable sequence editing framework that learns temporal concepts to precisely target the timing and scope of interventions in longitudinal data, significantly outperforming state-of-the-art baselines in generating accurate and realistic counterfactual trajectories for biological and clinical applications.
This paper demonstrates that integrating Low-Rank Adaptation (LoRA) into Federated Learning for Large Language Models significantly reduces unintended memorization of sensitive training data across diverse model sizes and domains, while maintaining performance and offering compatibility with other privacy-preserving techniques.
This paper introduces A3RL, a novel framework that integrates offline and online reinforcement learning through a confidence-aware active advantage-aligned sampling strategy to dynamically prioritize high-value data, thereby overcoming challenges like catastrophic forgetting and improving sample efficiency to outperform existing methods.
This paper introduces Texts as Time Series (TaTS), a novel framework that leverages the periodic alignment between paired texts and time series data to enhance multimodal forecasting and imputation performance in existing numerical-only models without requiring architectural changes.
The paper proposes LaVCa, a novel data-driven approach that leverages large language models to generate natural-language captions for images, thereby providing more accurate and detailed interpretations of human visual cortex voxel selectivity and revealing fine-grained functional differentiation within the visual cortex compared to existing deep neural network-based methods.
This paper proposes a Clustering-On-Difficulty (COD) framework that groups tasks by their difficulty scaling features to predict downstream LLM performance with high accuracy (1.55% error), effectively addressing challenges like emergent capabilities and inconsistent scaling patterns.
This study proposes a high-accuracy glioma subclass classification framework that fuses 2D and 3D UNET-segmented multimodal MRI images using weighted averaging and classifies them via a pre-trained ResNet50 model, achieving a 99.25% accuracy rate.
This paper proposes Leave-One-Out PPO (LOOP), a novel reinforcement learning method that combines variance reduction techniques from REINFORCE with the robustness of PPO to achieve a superior balance between sample efficiency and performance in fine-tuning text-to-image diffusion models.
This paper introduces OrthoGrad, a novel machine unlearning method that effectively removes the influence of specific data by projecting unlearn gradients onto the subspace orthogonal to retain gradients, thereby mitigating interference and outperforming existing approaches even when only a small portion of the training data is available.
This paper introduces GlucoLens, an explainable machine learning system that integrates wearable sensor data, diet, and activity logs to accurately predict postprandial hyperglycemia and recommend personalized behavioral interventions for managing blood glucose levels.
The paper proposes IMPACT, a novel motion planning framework that leverages Vision-Language Models to infer environment semantics and generate anisotropic cost maps, enabling a contact-aware A* planner to safely navigate cluttered environments by distinguishing between acceptable and dangerous object contacts.
This paper introduces Smooth Prototype Equivalences (SPE), a framework utilizing invertible neural networks to match sparse, noisy empirical observations to prototypical dynamical behaviors, enabling the equation-free identification of invariant structures and classification of dynamical regimes in complex biological and physical systems.
This paper introduces MUSS, a novel multilevel subset selection method that significantly improves both the scalability and performance of relevant and diverse selection tasks in applications like recommender systems and RAG, while providing a constant factor approximation guarantee and a tighter theoretical bound for existing distributed approaches.