3 papers
cs.CV2026
InstancePin: Instance-Addressable Layout-to-Image Diffusion via Coordinate Pinning
Chaoyue Wu, Yunfei Zhang, Si Wu
Layout-to-image diffusion models have achieved impressive semantic controllability by conditioning generation on category-level segmentation maps. However, such category-aligned co…
astro-ph.HE2026
Stability Boundary of Neutron-Dark Matter Mixed Stars
Xiao-Ding Zhou, Tian-Shun Chen, Si-Man Wu +1
Regarding the stability of two-fluid star models, we rigorously prove the equivalence between the emergence of a zero-frequency radial oscillation mode and the static critical-curv…
cs.CV2025
Discrete Prior-based Temporal-coherent Content Prediction for Blind Face Video Restoration
Lianxin Xie, Bingbing Zheng, Wen Xue +5
Blind face video restoration aims to restore high-fidelity details from videos subjected to complex and unknown degradations. This task poses a significant challenge of managing te…