Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout
arXiv:2507.10430v2 Announce Type: replace-cross Abstract: Federated Learning (FL) is a promising distributed machine learning approach that enables collaborative training of…
Gradient Regularization-based Neural Granger Causality
arXiv:2507.11178v1 Announce Type: cross Abstract: With the advancement of deep learning technologies, various neural network-based Granger causality models have been…
Improving Wi-Fi Network Performance Prediction with Deep Learning Models
arXiv:2507.11168v1 Announce Type: cross Abstract: The increasing need for robustness, reliability, and determinism in wireless networks for industrial and mission-critical…
A PBN-RL-XAI Framework for Discovering a “Hit-and-Run” Therapeutic Strategy in Melanoma
arXiv:2507.10136v2 Announce Type: replace-cross Abstract: Innate resistance to anti-PD-1 immunotherapy remains a major clinical challenge in metastatic melanoma, with the…
Think Clearly: Improving Reasoning via Redundant Token Pruning
arXiv:2507.08806v1 Announce Type: new Abstract: Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of…
Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
arXiv:2507.08730v2 Announce Type: replace-cross Abstract: Modern configurable software systems need to learn models that correlate configuration and performance. However, when…
A Variance-Reduced Cubic-Regularized Newton for Policy Optimization
arXiv:2507.10120v1 Announce Type: cross Abstract: In this paper, we study a second-order approach to policy optimization in reinforcement learning. Existing…
Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
arXiv:2507.10085v1 Announce Type: cross Abstract: Representation Fine-tuning (ReFT), a recently proposed Parameter-Efficient Fine-Tuning (PEFT) method, has attracted widespread attention for…
Mechanistic Indicators of Understanding in Large Language Models
arXiv:2507.08017v2 Announce Type: replace-cross Abstract: Recent findings in mechanistic interpretability (MI), the field probing the inner workings of Large Language…
Human Creativity and AI
arXiv:2507.08001v1 Announce Type: new Abstract: With the advancement of science and technology, the philosophy of creativity has undergone significant reinterpretation.…