4 papers
Instance-Level Post Hoc Uncertainty Quantification in Object Detection
Chongzhe Zhang, Zifan Zeng, Qunli Zhang +2
Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for safety assurance. Post hoc uncert…
Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs
Ke Li, Chongzhe Zhang, Zifan Zeng +3
Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score level, reducing unwarranted conf…
The Safety Challenge of World Models for Embodied AI Agents: A Review
Lorenzo Baraldi, Zifan Zeng, Chongzhe Zhang +8
The rapid progress in embodied artificial intelligence has highlighted the necessity for more advanced and integrated models that can perceive, interpret, and predict environmental…
World Models: The Safety Perspective
Zifan Zeng, Chongzhe Zhang, Feng Liu +4
With the proliferation of the Large Language Model (LLM), the concept of World Models (WM) has recently attracted a great deal of attention in the AI research community, especially…