3 papers
cs.LG2026
Activation Steering with a Feedback Controller
Dung V. Nguyen, Hieu M. Vu, Nhi Y. Pham +2
Controlling the behaviors of large language models (LLM) is fundamental to their safety alignment and reliable deployment. However, existing steering methods are primarily driven b…
cs.CV2026
H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in Large Vision-Language Models
Nhi Pham, Michael Schott
By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless, these models often suffer from…
cs.CV2025
Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
Nhi Pham, Artur Jesslen, Bernt Schiele +2
With the rise of deep neural networks, especially in safety-critical applications, robustness and interpretability are crucial to ensure their trustworthiness. Recent advances in 3…