Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models
12月 17, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2410.03026v3 Announce Type: replace Abstract: Language models (LMs) rely on their parametric knowledge augmented with...
Estimating LLM Uncertainty with Logits
5月 8, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2502.00290v4 Announce Type: replace Abstract: Over the past few years, Large Language Models (LLMs) have...
Establishing AI and data sovereignty in the age of autonomous systems
5月 14, 2026admin NUAI,Committee,ニュース,Uncategorized(0)When generative AI first moved from research labs into real-world business applications, enterprises made a...
Erasing Conceptual Knowledge from Language Models
7月 23, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2410.02760v3 Announce Type: replace Abstract: In this work, we introduce Erasure of Language Memory (ELM)...
Epistemic Diversity and Knowledge Collapse in Large Language Models
10月 31, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2510.04226v4 Announce Type: replace Abstract: Large language models (LLMs) tend to generate lexically, semantically, and...
EPFL Researchers Unveil FG2 at CVPR: A New AI Model That Slashes Localization Errors by 28% for Autonomous Vehicles in GPS-Denied Environments
6月 16, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Navigating the dense urban canyons of cities like San Francisco or New York can be...
EPFL Researchers Introduce MEMOIR: A Scalable Framework for Lifelong Model Editing in LLMs
6月 17, 2025admin NUAI,Committee,ニュース,Uncategorized(0)The Challenge of Updating LLM Knowledge LLMs have shown outstanding performance for various tasks through...
Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
9月 8, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.05060v1 Announce Type: new Abstract: We introduce Entropy2Vec, a novel framework for deriving cross-lingual language...
Entropy-Guided Reasoning Compression
11月 19, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2511.14258v1 Announce Type: new Abstract: Large reasoning models have demonstrated remarkable performance on complex reasoning...
