Related papers: GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL…

Asynchronous execution is essential for scaling reinforcement learning (RL) to modern large model workloads, including large language models and AI agents, but it can fundamentally alter RL optimization behavior. While prior work on…

Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…

In recent years, processing in memory (PIM) based mixedsignal designs have been proposed as energy- and area-efficient solutions with ultra high throughput to accelerate DNN computations. However, PIM designs are sensitive to imperfections…

This paper presents a novel satellite attitude control framework that integrates Soft Actor-Critic (SAC) reinforcement learning with Generative Adversarial Imitation Learning (GAIL) to achieve robust performance under various unknown…

We study how to design learning-based adaptive controllers that enable fast and accurate online adaptation in changing environments. In these settings, learning is typically done during an initial (offline) design phase, where the vehicle…

Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. Due to the cumulative and unavoidable negative impact of unresolved noise, existing methods cannot maintain a stable…

Graph Neural Networks (GNNs) often suffer from degree bias in node classification tasks, where prediction performance varies across nodes with different degrees. Several approaches, which adopt Graph Contrastive Learning (GCL), have been…

Temporal graph representation learning aims to generate low-dimensional dynamic node embeddings to capture temporal information as well as structural and property information. Current representation learning methods for temporal networks…

This paper investigates the implementation and application of the multi-variable grid-forming hybrid angle control (HAC) for high-power converters in transmission grids. We explore the system-level performance and robustness of the HAC…

Leveraging over-the-air computations for model aggregation is an effective approach to cope with the communication bottleneck in federated edge learning. By exploiting the superposition properties of multi-access channels, this approach…

The selective fixed-filter strategy is popular in industrial applications involving active noise control (ANC) technology, which circumvents the time-consuming online learning process by selecting the best-matched pre-trained control…

Measuring learning progress is essential for curiosity-driven exploration in reinforcement learning, but widely used signals such as prediction error often fail to distinguish meaningful, learnable patterns from random noise. This paper…

Acoustic echo cancellation (AEC), noise suppression (NS) and automatic gain control (AGC) are three often required modules for real-time communications (RTC). This paper proposes a neural network supported algorithm for RTC, namely NN3A,…

Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for…

Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of annotations and (2) homophily disparity at node and class…

In neural network models, soft mixtures of fixed candidate components (e.g., logic gates and sub-networks) are often used during training for stable optimization, while hard selection is typically used at inference. This raises questions…

Weighted summation has remained the default input aggregation mechanism in artificial neurons since the earliest neural network models. While computationally efficient, this design implicitly behaves like a mean-based estimator and is…

Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjusts the loss weight of each training sample based on its…

Neural network training is commonly accelerated by using multiple synchronized workers to compute gradient updates in parallel. Asynchronous methods remove synchronization overheads and improve hardware utilization at the cost of…

We introduce Gradient Agreement Filtering (GAF) to improve on gradient averaging in distributed deep learning optimization. Traditional distributed data-parallel stochastic gradient descent involves averaging gradients of microbatches to…