base_model, datasets, language, license, metrics, pipeline_tag, library_name

base_model	datasets	language	license	metrics	pipeline_tag	library_name
Qwen/Qwen2.5-VL-7B-Instruct	RenlyH/CodeV-RL-Data	en zh	mit	accuracy	image-text-to-text	transformers

CodeV is a code-based visual agent trained with Tool-Aware Policy Optimization (TAPO) for faithful visual reasoning. This agentic vision-language model is designed to "think with images" by calling image operations, addressing unfaithful visual reasoning in prior models. CodeV achieves competitive accuracy and substantially increases faithful tool-use rates on visual search benchmarks, also demonstrating strong performance on multimodal reasoning and math benchmarks.

This model was presented in the paper CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization.

Code: https://github.com/RenlyH/CodeV