Liquid AI has announced the release of two new open-weight multimodal decision models, d1-3B and d1-omni-600M, as part of its d1 decision model family. These models are designed to process both text and images, as well as text with audio, while uniquely operating without generating text output.
The d1-3B model can interpret text and images, while the d1-omni-600M can handle combinations of text with audio or images. Both models return calibrated, typed answers in a single forward pass, targeting real-time decision-making applications. This innovative approach could significantly enhance the efficiency of AI systems in various practical scenarios.
Compiled automatically by the Tech AI Newsdesk from public AI-news sources and summarised in our own words.
