You can deploy this model and start earning money today!

achernarwang/
SPY_Qwen2-VL-7B-Instruct_NCA-P

Name: SPY_Qwen2-VL-7B-Instruct_NCA-P
Availability: InStock

Qwen/Qwen2-VL-7B-Instruct

finetune

apache-2.0

text-generation-inference

endpoints_compatible

Views

No views yet

SPY_Qwen2-VL-7B-Instruct_NCA-P

This model is a fine-tuned version of Qwen2-VL-7B, trained on our SPY-Tune dataset using the proposed NCA-P alignment algorithm (which is a variant of NCA).

It serves as the official checkpoint used in our ACM Multimedia 2025 BNI Oral paper:

Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models

The model aims to enhance personalized privacy-preserving abilities of large vision-language models during inference time, enabling controllable trade-offs between utility and privacy according to user-specified privacy intents.

For more details about the dataset, training process, and evaluation metrics, please refer to our GitHub repository: https://github.com/achernarwang/specify-privacy-yourself

achernarwang/SPY_Qwen2-VL-7B-Instruct_NCA-P

SPY_Qwen2-VL-7B-Instruct_NCA-P

achernarwang/
SPY_Qwen2-VL-7B-Instruct_NCA-P