New embedding model leaderboard shakeup: Google takes #1 while Alibaba’s open source alternative closes gap
7 月 19, 2025admin NUAI,Committee,新闻,Uncategorized(0)Google’s new Gemini Embedding model now leads the MTEB benchmark. But it is facing fierce...
New AI Method From Meta and NYU Boosts LLM Alignment Using Semi-Online Reinforcement Learning
7 月 7, 2025admin NUAI,Committee,新闻,Uncategorized(0)Optimizing LLMs for Human Alignment Using Reinforcement Learning Large language models often require a further...
New AI architecture delivers 100x faster reasoning than LLMs with just 1,000 training examples
7 月 26, 2025admin NUAI,Committee,新闻,Uncategorized(0)Hierarchical Reasoning Models (HRM) tackle complex reasoning tasks while being smaller, faster, and more data-efficient...
Neurosymbolic Information Extraction from Transactional Documents
12 月 11, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.09666v1 Announce Type: new Abstract: This paper presents a neurosymbolic framework for information extraction from...
Neurocomputational Mechanisms of Syntactic Transfer in Bilingual Sentence Production
1 月 27, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2601.18056v1 Announce Type: new Abstract: We discuss the benefits of incorporating into the study of...
NeuroABench: A Multimodal Evaluation Benchmark for Neurosurgical Anatomy Identification
12 月 9, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.06921v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown significant potential in...
NeuralOS: A Generative Framework for Simulating Interactive Operating System Interfaces
7 月 17, 2025admin NUAI,Committee,新闻,Uncategorized(0)Transforming Human-Computer Interaction with Generative Interfaces Recent advances in generative models are transforming the way...
Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering
6 月 13, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2506.10751v1 Announce Type: cross Abstract: Automated question answering (QA) over electronic health records (EHRs) can...
NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs
2 月 2, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2505.17595v3 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve impressive performance across domains but...
