Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device
8月 13, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Yesterday, Liquid AI released LFM2.5-VL-3B. It is a 3.1B-parameter vision-language model built for on-device deployment...
Liquid AI Releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M: Bidirectional Encoders That Stay Fast at 8K Context on CPU
7月 29, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Liquid AI has released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M. Both are masked language...
Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs
8月 21, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Liquid AI has released DSpark draft model checkpoints for three models in its LFM2.5 family:...
Liquid AI Releases LFM2-ColBERT-350M: A New Small Model that brings Late Interaction Retrieval to Multilingual and Cross-Lingual RAG
10月 29, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Can a compact late interaction retriever index once and deliver accurate cross lingual search with...
Liquid AI Releases LFM2-8B-A1B: An On-Device Mixture-of-Experts with 8.3B Params and a 1.5B Active Params per Token
10月 11, 2025admin NUAI,Committee,ニュース,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
4月 1, 2026admin NUAI,Committee,ニュース,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
8月 26, 2026admin NUAI,Committee,ニュース,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
7月 7, 2026admin NUAI,Committee,ニュース,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
6月 19, 2026admin NUAI,Committee,ニュース,Uncategorized(0)This week, Liquid AI released two new retrieval models. They are LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M. Both...
