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…
SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents
arXiv:2507.10562v1 Announce Type: new Abstract: Current AI agent architectures suffer from ephemeral memory limitations, preventing effective collaboration and knowledge sharing…
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…
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…
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…
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…
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…
Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
arXiv:2507.07532v2 Announce Type: replace-cross Abstract: While Prover-Verifier Games (PVGs) offer a promising path toward verifiability in nonlinear classification models, they…
A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1
arXiv:2507.08621v1 Announce Type: cross Abstract: Argument mining (AM) is an interdisciplinary research field that integrates insights from logic, philosophy, linguistics,…
Adaptive Framework for Ambient Intelligence in Rehabilitation Assistance
arXiv:2507.08624v1 Announce Type: cross Abstract: This paper introduces the Ambient Intelligence Rehabilitation Support (AIRS) framework, an advanced artificial intelligence-based solution…