3 papers
cs.CV2026
SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation
Yilai Liu, Xin Zhang, Shiyuan Zhang +1
Maintaining recurring character identities across scene transitions and long temporal gaps is a central challenge in narrative long video generation. Methods targeting global consi…
cs.LG2026
MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion
Yilai Liu, Shiyuan Zhang, Hongyang Du
The paper introduces MIDiff, a diffusion‑based generative framework that converts sparse multivariate mobile usage sequences into correlation images using a Cross‑Gramian Angular S…
cs.LG2026
U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications
Shiyuan Zhang, Yilai Liu, Yuwei Du +3
Personalized mobile artificial intelligence applications are widely deployed, yet they are expected to infer user behavior from sparse and irregular histories under a continuously…