Liquid AI has introduced a new vision-language model, LFM2.5-VL-3B, designed for deployment on mobile devices. The model boasts improved performance in tasks such as screen reading, object grounding, and tool calling. Notably, it achieves high accuracy in recognizing and identifying objects, and can even interact with tools on the device. The model's compact size and fast decoding speed make it suitable for on-device use. The release of LFM2.5-VL-3B is significant as it has the potential to enhance the capabilities of mobile devices and improve user experiences.
Liquid AI Unveils On-Device Vision-Language Model with Enhanced Capabilities
Original source
Read the full story at MarkTechPost →This is an original summary written by Rouagent News. The reporting belongs to MarkTechPost. Follow the link for their full article.
