3 papers
cs.CV2025
CPSL: Representing Volumetric Video via Content-Promoted Scene Layers
Kaiyuan Hu, Yili Jin, Junhua Liu +3
Volumetric video enables immersive and interactive visual experiences by supporting free viewpoint exploration and realistic motion parallax. However, existing volumetric represent…
cs.CR2025
Privis: Towards Content-Aware Secure Volumetric Video Delivery
Kaiyuan Hu, Hong Kang, Yili Jin +4
Volumetric video has emerged as a key paradigm in eXtended Reality (XR) and immersive multimedia because it enables highly interactive, spatially consistent 3D experiences. However…
cs.LG2025
Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization
Langzhou He, Junyou Zhu, Fangxin Wang +5
Molecular foundation models are rapidly advancing scientific discovery, but their unreliability on out-of-distribution (OOD) samples severely limits their application in high-stake…