Hi! I'm Niels from the Hugging Face community science team.
I've opened this PR to improve the discoverability and usability of this model:
- Added `pipeline_tag: image-text-to-text` to reflect its multimodal capabilities (Qwen3-VL based).
- Added `library_name: transformers` as the repository contains the standard configuration files for the library.
- Updated the model card title to match the framework name "RLAnything" and added links to the paper and code.
Let me know if you have any questions!
