Language Detection by Means of the Minkowski Norm: Identification Through Character Bigrams and Frequency Analysis
Juli 24, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2507.16284v2 Announce Type: replace Abstract: The debate surrounding language identification has gained renewed attention in...
LangChain Releases Deep Agents: A Structured Runtime for Planning, Memory, and Context Isolation in Multi-Step AI Agents
März 15, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Most LLM agents work well for short tool-calling loops but start to break down when...
L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
Oktober 6, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2503.04697v2 Announce Type: replace Abstract: Reasoning language models have shown an uncanny ability to improve...
Kyutai Releases MuScriptor: An Open-Weight Decoder-Only Transformer for Multi-Instrument Music Transcription to MIDI
Juli 12, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Automatic Music Transcription (AMT) converts an audio recording into symbolic notes, usually MIDI. Single-instrument transcription...
Kyutai Releases Hibiki-Zero: A3B Parameter Simultaneous Speech-to-Speech Translation Model Using GRPO Reinforcement Learning Without Any Word-Level Aligned Data
Februar 14, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Kyutai has released Hibiki-Zero, a new model for simultaneous speech-to-speech translation (S2ST) and speech-to-text translation...
Kyutai Releases Hibiki-Zero: A3B Parameter Simultaneous Speech-to-Speech Translation Model Using GRPO Reinforcement Learning Without Any Word-Level Aligned Data
Februar 14, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Kyutai has released Hibiki-Zero, a new model for simultaneous speech-to-speech translation (S2ST) and speech-to-text translation...
Kyutai Releases 2B Parameter Streaming Text-to-Speech TTS with 220ms Latency and 2.5M Hours of Training
Juli 6, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)Kyutai, an open AI research lab, has released a groundbreaking streaming Text-to-Speech (TTS) model with...
KwaiKAT Team Releases KAT-Coder-V2.5: An Agentic Coding Model Trained on 100,000+ Verifiable Repository Environments
Juli 26, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)The KwaiKAT Team at Kuaishou has introduced the KAT-Coder-V2.5. It is a coding model trained...
KoWit-24: A Richly Annotated Dataset of Wordplay in News Headlines
August 28, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2503.01510v2 Announce Type: replace Abstract: We present KoWit-24, a dataset with fine-grained annotation of wordplay...
