Fan Shi

This paper provides the first comprehensive systematization and large-scale empirical evaluation of existing LLM-based Automated Penetration Testing (AutoPT) frameworks, offering a structured taxonomy and unified benchmark for the field.

The paper introduces OmniVerifier-M1, a multimodal meta-verifier that uses symbolic outputs and decoupled reinforcement learning to provide robust, fine-grained verification and error localization for large multimodal models.

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during training.

The paper introduces UniKE, a benchmark showing that successful knowledge edits in text-only multimodal models do not reliably transfer to image generation, revealing a significant modality gap.