Update README.md

README.md

@@ -179,6 +179,7 @@ Register in `vlmeval/config.py`:
 from functools import partial
 from vlmeval.vlm import InternVLChat
 
+# Add to ungrouped dict
 "KVL-DPO": partial(InternVLChat, model_path="amoeba04/KVL-DPO", max_new_tokens=16384, version="V2.0"),
 ```
 
@@ -187,37 +188,12 @@ Run evaluation:
 python run.py --data MMBench_DEV_EN --model KVL-DPO --verbose
 ```
 
-## Intended Use Cases
+## Intended Use
 
-- **Scientific Document Understanding**: Analysis of figures, tables, and diagrams in scientific papers
-- **Medical Image Analysis**: Interpretation of radiology, pathology, and endoscopy images
+- **Scientific Document Understanding**: Analyzing figures, tables, and diagrams from scientific papers
+- **Medical Image Analysis**: Radiology, pathology, and endoscopy image interpretation
 - **Visual Question Answering**: General and domain-specific VQA tasks
 - **Chain-of-Thought Reasoning**: Complex visual reasoning with step-by-step explanations
-- **Human-Aligned Responses**: Improved response quality through preference optimization
-
-## Model Comparison
-
-| Model | Training Method | Key Advantage |
-|-------|----------------|---------------|
-| KVL | SFT (4M samples) | Strong domain knowledge |
-| KVL-DPO | SFT + DPO | Better aligned with human preferences |
-
-## License
-
-This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
-
-## Citation
-
-If you use this model, please cite:
-```bibtex
-@misc{kvl-dpo,
-  title={KVL-DPO: Vision-Language Model with Direct Preference Optimization},
-  author={amoeba04},
-  year={2025},
-  publisher={Hugging Face},
-  url={https://huggingface.co/amoeba04/KVL-DPO}
-}
-```
 
 ## Acknowledgments
 
@@ -225,3 +201,7 @@ If you use this model, please cite:
 - [ms-swift](https://github.com/modelscope/ms-swift) - Training framework
 - [MMInstruction](https://huggingface.co/MMInstruction) - VLFeedback dataset
 - All dataset creators for their valuable contributions
+
+## License
+
+This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).