---
license: apache-2.0
base_model:
- OpenGVLab/InternVL3_5-8B
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- EVA
- internvl
- model-editing
- ai-safety
- jailbreak
- defense
- vision-language-model
---

# EVA-InternVL3.5-8B

This repository contains the final InternVL3.5-8B checkpoint produced by **EVA**.

EVA is an editing-based framework for improving the robustness and safety alignment of large language models and vision-language models against diverse jailbreak attacks while preserving their general capabilities on benign tasks.

## Model information

- **EVA checkpoint:** `wanglne/EVA-InternVL3.5-8B`
- **Base model:** [OpenGVLab/InternVL3_5-8B](https://huggingface.co/OpenGVLab/InternVL3_5-8B)

## Resources

- **Paper:** [EVA: Editing for Versatile Alignment against Jailbreaks](https://arxiv.org/abs/2605.14750)
- **IEEE TPAMI:** [10.1109/TPAMI.2026.3694189](https://doi.org/10.1109/TPAMI.2026.3694189)
- **Code:** [wanglne/EVA](https://github.com/wanglne/EVA)
- **EVA model collection:** [EVA models](https://huggingface.co/collections/wanglne/eva-editing-for-versatile-alignment-against-jailbreaks)

## Intended use

This checkpoint is released for research, reproduction, safety evaluation, and comparison with other alignment methods.

## License

This checkpoint is derived from InternVL3.5-8B. Its use and redistribution remain subject to the Apache License 2.0 and the applicable base-model terms.

The EVA source code is released separately under the MIT License.

## Citation

```bibtex
@ARTICLE{11523146,
  author={Wang, Yi and Qiu, Hongye and Xu, Yue and Yang, Sibei and Qin, Zhan and Huang, Minlie and Wang, Wenjie},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={EVA: Editing for Versatile Alignment against Jailbreaks}, 
  year={2026},
  volume={},
  number={},
  pages={1-16},
  keywords={Automatic speech recognition;Modeling;Safety;Visualization;Large language models;Conferences;Optimization;Educational institutions;Light emitting diodes;Tuning;Safety Alignment;Jailbreak Attacks;Model Editing;Large Language Models;Vision Language Models},
  doi={10.1109/TPAMI.2026.3694189}}
```