SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation
arXiv, 2026
Propose SlotMem, a character-addressable internal memory framework for preserving long-range character consistency in narrative long-video generation.
Research
You can also find my articles on my Google Scholar profile.
Long Video Understanding & Generation
Mobile Usage Behavior Modeling
MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion
arXiv, 2026
Propose MIDiff, a multivariate-imaging diffusion framework for generating realistic and diverse mobile usage traces under sparsity and usage imbalance.
U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications
arXiv, 2026
Propose U-MASK, a uniform model for multi-tasks generazabiltity through spatio-temporal masks for contexts-retrival under sparse observations.
Poster: Enhancing Mobile Traffic Data Generation through Spatio-temporal Correlation Imaging
MobiCom Poster, 2025
Address the challenge of users’ daily mobile usage modeling under usage sparsity by correlation imaging for data augmentation.