Liquid AI Releases LFM2-8B-A1B: An On-Device Mixture-of-Experts with 8.3B Params and a 1.5B Active Params per Token
Oktober 11, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)How much capability can a sparse 8.3B-parameter MoE with a ~1.5B active path deliver on...
Liquid AI Released LFM2.5-350M: A Compact 350M Parameter Model Trained on 28T Tokens with Scaled Reinforcement Learning
April 1, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)In the current landscape of generative AI, the ‘scaling laws’ have generally dictated that more...
Liquid AI Open-Sources Pipette: A Reproducible Benchmarking Suite That Measures On-Device Models, Quantization, Runtime and Hardware Together
August 26, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Model cards report quality under server-class, full-precision conditions. Those numbers rarely predict how the same...
Liquid AI Open-Sources Antidoom: A Final Token Preference Optimization (FTPO) Method that Reduces Doom Loops in Reasoning Models
Juli 7, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)Liquid AI has released Antidoom, an open-source method that targets a common failure mode in...
Liquid AI Introduces LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M: Dense Bi-Encoder and Late-Interaction Models for Fast Multilingual Search Across 11 Languages
Juni 19, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)This week, Liquid AI released two new retrieval models. They are LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M. Both...
Link Prediction for Event Logs in the Process Industry
März 4, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2508.09096v2 Announce Type: replace Abstract: In the era of graph-based retrieval-augmented generation (RAG), link prediction...
Like humans, AI is forcing institutions to rethink their purpose
Juni 9, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)Like people undergoing cognitive migration, institutions must reassess what they were made for in this...
Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench
April 7, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2604.03455v1 Announce Type: cross Abstract: Retrieval-Augmented Generation pipelines span a wide range of retrieval strategies...
LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence
Dezember 5, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2512.04578v1 Announce Type: new Abstract: Legal general intelligence (GI) refers to artificial intelligence (AI) that...
