# Multilingual Visual Understanding

InternVL3-8B is an advanced multimodal large language model developed by OpenGVLab, featuring powerful multimodal perception and reasoning capabilities, supporting tool calling, GUI agents, industrial image analysis, 3D visual perception, and other emerging fields.

InternVL3-2B-Instruct is a supervised fine-tuned version based on InternVL3-2B, undergoing native multimodal pretraining and SFT processing, equipped with powerful multimodal perception and reasoning capabilities.

A multilingual visual retriever based on Qwen2.5-VL-3B-Instruct with ColBERT strategy, excelling in Vidore benchmark tests

EraX-VL-2B-V1.5 is a multimodal foundation model supporting Vietnamese, English, and Chinese, with capabilities for image-to-text and image-text-to-text conversion.

Pix2Struct is a vision-language understanding model pretrained for image-to-text conversion tasks, specifically optimized for high-resolution infographic visual question answering.

Pix2Struct is an image encoder-text decoder model trained through multi-task learning for visual-language understanding tasks, specifically optimized for visual question answering on high-resolution infographics.

Pix2Struct is a vision-language understanding model trained via image-to-text conversion for multitasking, supporting tasks like image caption generation and visual question answering.

Pix2Struct is a vision-language understanding model that processes image-to-text tasks through pre-training and fine-tuning, particularly suitable for image caption generation.