GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
PolicyShiftGuard
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
PolicyShiftGuard
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Use this checkpoint when you want to reproduce the two-stage training pipeline or compare Stage-1 RP-SFT against the final BP-Adapt model.
For standard evaluation or deployment, use the final model instead:
The model is trained with PolicyShiftBench supervision:
If you find this work helpful, please cite the paper:
bibtex
@article{song2026policyshiftguard,title = {PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails},author = {Song, Mingyang and Xu, Luxin and Sun, Haoyu and Pan, Minzhou and Cheng, Yu and Li, Bo},journal = {arXiv preprint arXiv:2607.05910},year = {2026}}