# Dynamic resolution processing

InternVL3-1B is an advanced multimodal large language model developed by OpenGVLab, which has completed native multimodal pretraining but has not undergone post-training.

InternVL3-38B is an advanced multimodal large language model that excels in multimodal perception, reasoning, and other capabilities. It shows significant improvements compared to previous models and also expands multimodal capabilities such as tool use and GUI agents.

Qwen2-VL is the latest iteration of the Qwen-VL model series, featuring full-resolution image understanding, ultra-long video parsing, and multilingual text and image recognition capabilities.

UGround is a powerful GUI visual positioning model trained with a simple recipe, developed in collaboration by OSU NLP Group and Orby AI.

A visual retrieval model based on Qwen2-VL-2B-Instruct and ColBERT strategy, capable of generating multi-vector text and image representations