PEARL
Collection
Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
•
3 items
•
Updated
Model Card for PEARL-7B-Based on Qwen2.5-VL-7B
Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning. arxiv.org/abs/2511.18437
Model Details
Model Description
This is a multimodal reasoning model.
- Developed by: [Chi Zhang~1909zczc@gmail.com]
- Finetuned from model [optional]: [Qwen2.5-VL-7B]
Model Sources [optional]
- Repository: [PEARL]
- Paper: [More Information Needed]
Uses
Training Details
Training Data
Citation [optional]
- Downloads last month
- 32
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Rex1090/PEARL-7B
Base model
Qwen/Qwen2.5-VL-7B-Instruct