Related papers: Adaptive Equilibrium: Dynamic Weighting Framework …

The rapidly changing landscapes of modern optimization problems require algorithms that can be adapted in real-time. This paper introduces an Adaptive Metaheuristic Framework (AMF) designed for dynamic environments. It is capable of…

The ultimate goal of any numerical scheme for partial differential equations (PDEs) is to compute an approximation of user-prescribed accuracy at quasi-minimal computational time. To this end, algorithmically, the standard adaptive finite…

Contemporary autoregressive transformers operate in open loop: each hidden state is computed in a single forward pass and never revised, causing errors to propagate uncorrected through the sequence. We identify this open-loop bottleneck as…

In this study the problem of Federated Learning (FL) is explored under a new perspective by utilizing the Deep Equilibrium (DEQ) models instead of conventional deep learning networks. We claim that incorporating DEQ models into the…

Precise control in modern robotic applications is always an open issue due to unknown time-varying disturbances. Existing meta-learning-based approaches require a shared representation of environmental structures, which lack flexibility for…

Recent studies reveal that Convolutional Neural Networks (CNNs) are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. Many adversarial defense methods improve robustness at the cost of…

Fine-tuning is the primary mechanism for adapting foundation models to downstream tasks; however, standard approaches largely optimize task objectives in isolation and do not account for secondary yet critical alignment objectives (e.g.,…

Deep learning has shown impressive performance on challenging perceptual tasks and has been widely used in software to provide intelligent services. However, researchers found deep neural networks vulnerable to adversarial examples. Since…

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

Accurate models are essential for design, performance prediction, control, and diagnostics in complex engineering systems. Physics-based models excel during the design phase but often become outdated during system deployment due to changing…

Physics-informed deep learning has emerged as a promising alternative for solving partial differential equations. However, for complex problems, training these networks can still be challenging, often resulting in unsatisfactory accuracy…

Machine learning-based Deepfake detection models have achieved impressive results on benchmark datasets, yet their performance often deteriorates significantly when evaluated on out-of-distribution data. In this work, we investigate an…

Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…

Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by…

This script offers an implementation-oriented introduction to deep learning methods for solving and estimating high-dimensional dynamic stochastic models in economics and finance. Its starting point is the curse of dimensionality:…

We propose a novel framework to study asynchronous federated learning optimization with delays in gradient updates. Our theoretical framework extends the standard FedAvg aggregation scheme by introducing stochastic aggregation weights to…

Deep learning is becoming increasingly ubiquitous in medical research and applications while involving sensitive information and even critical diagnosis decisions. Researchers observe a significant performance disparity among subgroups with…

Fairness is a widely discussed topic in recommender systems, but its practical implementation faces challenges in defining sensitive features while maintaining recommendation accuracy. We propose feature fairness as the foundation to…

This paper treats the global stabilization problem of continuous-time switched affine systems that have rank-deficient convex combinations of their dynamic matrices. For these systems, the already known set of attainable equilibrium points…

Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities.…