# Dynamic Resolution Processing

InternVL3-38B-Instruct is an advanced Multimodal Large Language Model (MLLM) that demonstrates exceptional overall performance, with strong multimodal perception and reasoning capabilities.

BiQwen2 is a visual retrieval model based on Qwen2-VL-2B-Instruct and the ColBERT strategy, focusing on efficient visual document retrieval.

Qwen2.5-VL is the latest vision-language model in the Qwen family, focusing on enhanced visual understanding and agent capabilities.

A multilingual visual retrieval model based on Qwen2.5-VL-3B-Instruct and ColBERT strategy, supporting dynamic input image resolution and generating ColBERT-style multi-vector text and image representations.

Qwen2.5-VL is the latest vision-language model in the Qwen family, featuring powerful visual understanding and agent capabilities, supporting multi-format visual localization and structured output generation.

A multilingual visual retrieval model based on Qwen2.5-VL-7B-Instruct using the ColBERT strategy, ranked first in the Vidore benchmark

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

Qwen2.5-VL is the latest vision-language model in the Qwen family, featuring enhanced visual understanding, agent capabilities, and structured output generation.

UGround is a powerful GUI visual positioning model trained using a simple method, jointly developed by OSUNLP and Orby AI.

ColQwen2 is a visual retrieval model based on Qwen2-VL-2B-Instruct and the ColBERT strategy, designed for efficient indexing of document visual features.

A visual retrieval model based on Qwen2-VL-2B-Instruct and ColBERT strategy, capable of efficiently indexing documents through visual features