Tao Liu

STARE introduces a novel hierarchical reinforcement learning framework that treats the entire image generation process (denoising trajectory) as an attack surface, significantly improving the detection of multi-modal toxicity vulnerabilities in Vision-Language Models.

This paper introduces a new benchmark to test Tool Description Poisoning (TDP) attacks on LLM agents, demonstrating that even advanced models like GPT-4o are highly vulnerable and that current defenses are often ineffective.

This paper provides a systematic, lifecycle-based framework for analyzing security threats and defenses across the entire fine-tuning process of LLMs, revealing that attack effectiveness is highly model-dependent and defenses rarely generalize across different phases.

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic tasks and embodiments.