Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering
6月 13, 2025admin NUAI,Committee,ニュース,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,ニュース,Uncategorized(0)arXiv:2505.17595v3 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve impressive performance across domains but...
Neuphonic Open-Sources NeuTTS Air: A 748M-Parameter On-Device Speech Language Model with Instant Voice Cloning
10月 3, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Neuphonic has released NeuTTS Air, an open-source text-to-speech (TTS) speech language model designed to run...
Netflix AI Team Just Open-Sourced VOID: an AI Model That Erases Objects From Videos — Physics and All
4月 4, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Video editing has always had a dirty secret: removing an object from footage is easy;...
Nested Learning: A New Machine Learning Approach for Continual Learning that Views Models as Nested Optimization Problems to Enhance Long Context Processing
11月 9, 2025admin NUAI,Committee,ニュース,Uncategorized(0)How can we build AI systems that keep learning new information over time without forgetting...
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
9月 5, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.04011v1 Announce Type: cross Abstract: We present NER Retriever, a zero-shot retrieval framework for ad-hoc...
Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset
8月 22, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2508.15096v1 Announce Type: new Abstract: Pretraining large language models (LLMs) on high-quality, structured data such...
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
12月 25, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2512.20848v1 Announce Type: new Abstract: We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer...
Nebius AI Advances Open-Weight LLMs Through Reinforcement Learning for Capable SWE Agents
8月 13, 2025admin NUAI,Committee,ニュース,Uncategorized(0)The landscape of software engineering automation is evolving rapidly, driven by advances in Large Language...
