3 papers
cs.CR2025
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
Zheng-Xin Yong, Stephen H. Bach
We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoni…
cs.CL2025
Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
Yik Siu Chan, Zheng-Xin Yong, Stephen H. Bach
Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs), but this process can also increase harmful outputs in adversarial settin…
cs.RO2025
Trinity: A Modular Humanoid Robot AI System
Jingkai Sun, Qiang Zhang, Gang Han +7
In recent years, research on humanoid robots has garnered increasing attention. With breakthroughs in various types of artificial intelligence algorithms, embodied intelligence, ex…