3 papers
cs.CV2026
Memorizon: Training World Models Beyond Their Context Window
Tingting Liao, Xuezhi Liang, Hao Li +1
Streaming world models should render a place consistently across repeated visits. Directly supervising such revisits requires training samples that capture both visits, often spann…
cs.CV2026
LOCI: Spatial Linear Memory for Streaming World Models
Ji Xia, Tingting Liao, Xuezhi Liang +2
When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past observations and retrieving the…
cs.CV2025
Character Mixing for Video Generation
Tingting Liao, Chongjian Ge, Guangyi Liu +2
Imagine Mr. Bean stepping into Tom and Jerry--can we generate videos where characters interact naturally across different worlds? We study inter-character interaction in text-to-vi…