Xianglong Li

AgentVisor is a novel defense framework that uses semantic virtualization, inspired by OS principles, to significantly reduce LLM agent vulnerability to prompt injection while maintaining high utility.

EvoPoC introduces a knowledge-driven agentic system that automates the synthesis of verifiable and economically viable exploits for DeFi smart contracts, achieving high recall and significant revenue recovery rates.

MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reducing token usage.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper proposes a compression pipeline combining few-step distillation and low-bit quantization to significantly reduce the deployment cost and parameter footprint of large dual-expert video diffusion models like Wan2.2, while maintaining high visual quality.