Long Chen

The paper introduces a stateful agent backdoor that allows malicious attacks to persist and execute incrementally across multiple sessions, significantly enhancing the threat model for LLM-based agents.

This study provides the first large-scale measurement of prompt injection attacks in real-world LLM-based resume screening, finding that approximately 1% of resumes contain hidden injections.

SSR3D-LLM introduces a structured spatial reasoning interface for unified 3D-LLMs, allowing fine-grained object grounding by generating and processing sequential latent spatial steps.

This study provides the first systematic measurement of prompt injection attacks in a real-world LLM-based resume screening application, finding that approximately 1% of resumes contain hidden injections.

The paper introduces Individual Fairness-aware Strategic Classification (IFSC), a framework that models interdependent strategic manipulation where agents imitate nearby positively decided peers to achieve favorable outcomes while maintaining individual fairness.

The paper proposes a simulation-trained variable impedance control framework for wearable exoskeletons that safely and effectively augments human physical capabilities across multiple tasks.