← Search

Zihan Yan

2 accepted papers

2025

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation

IJCAI 2025

Embodied agents exhibit immense potential across a multitude of domains, making the assurance of their behavioral safety a fundamental prerequisite for their widespread deployment. However, existing research predominantly concentrates on the security of general large language models, lacking special

2024

Relightable and Animatable Neural Avatar from Sparse-View Video

CVPR 2024highlight

This paper tackles the problem of creating relightable and animatable neural avatars from sparse-view (or monocular) videos of dynamic humans under unknown illumination. Previous neural human reconstruction methods produce animatable avatars from sparse views using deformed Signed Distance Fields (S…