# Cross-modal reasoning

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google. It is built on the same research and technology as the Gemini model and supports text, audio, and visual inputs.

Qwen2-VL-2B-Instruct is a multimodal vision-language model that supports image-text-to-text tasks.

Aya Vision 32B is an open-weight 32B parameter multimodal model developed by Cohere Labs, supporting vision-language tasks in 23 languages.

A first-person perspective optimized vision-language model trained on BLIP-2-OPT-2.7B, employing the innovative EILEV method to stimulate in-context learning capabilities

This model is a document visual question answering model fine-tuned on the Multi-page Document VQA (MP-DocVQA) dataset, based on Microsoft's pre-trained LayoutLMv3 model.