Rebuilding the data stack for AI
April 27, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Artificial intelligence may be dominating boardroom agendas, but many enterprises are discovering that the biggest...
Reasoning Promotes Robustness in Theory of Mind Tasks
Januar 26, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2601.16853v1 Announce Type: cross Abstract: Large language models (LLMs) have recently shown strong performance on...
Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
Dezember 25, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2512.20634v1 Announce Type: cross Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning for...
READoc: A Unified Benchmark for Realistic Document Structured Extraction
Juli 15, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2409.05137v3 Announce Type: replace Abstract: Document Structured Extraction (DSE) aims to extract structured content from...
Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
Januar 22, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2510.06605v2 Announce Type: replace-cross Abstract: The substantial investment required to develop Large Language Models (LLMs)...
Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers
Oktober 17, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2510.13939v1 Announce Type: new Abstract: The use of copyrighted books for training AI models has...
Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics
Oktober 20, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2510.15345v1 Announce Type: new Abstract: Automatic readability assessment plays a key role in ensuring effective...
Readability Formulas, Systems and LLMs are Poor Predictors of Reading Ease
November 5, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2502.11150v4 Announce Type: replace Abstract: Methods for scoring text readability have been studied for over...
RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
Januar 31, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2501.04052v2 Announce Type: replace-cross Abstract: The recently introduced NVFP4 format demonstrates remarkable performance and memory...
