Qi Zhu

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

The paper proposes HTell, a fast and lightweight data-free backdoor detector that analyzes the abnormal response concentration of backdoored models on the target class using random latent probes applied directly to the prediction head.

The paper proposes DFBScanner, a lightweight static parameter inspection framework that detects backdoor attacks by analyzing anomalous parameter updates in the final classification layer, achieving fast and generalizable detection.

The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, leading to improved agent performance.

The paper introduces Autonomous Agentic Data Engineering, demonstrating that LLMs can autonomously plan and optimize end-to-end data curation pipelines, leading to substantial performance gains in specialized models.

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vision-Language-Action policies.

This paper proposes a unified, lifecycle-centric framework and a detailed taxonomy to survey and analyze novel, finance-specific attack surfaces and vulnerabilities in AI systems used within the financial sector.

The paper proposes PC-MambaSDE, a physically-constrained continuous-time framework that accurately predicts Remaining Useful Life (RUL) despite irregular sensor observations and ensures physically plausible degradation trajectories.

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.