Hong Sun

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between forward and backward document rankings.

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.

The paper introduces the Proactive Availability Backdoor (PAB), a novel social engineering attack that weaponizes LLM helpfulness to proactively trap users into executing malicious queries, achieving a high attack success rate of 73.1%.

This paper investigates the production-evaluation gap in Large Reasoning Models (LRMs), finding that while LRMs excel at generating solutions, they struggle significantly to evaluate flawed reasoning, often exhibiting an answer confirmation bias.