Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models
Nan Zhou, Jianxiong Gao, Qiuyu Wang +10
As video models enable longer and more realistic interactive experiences, maintaining a world consistent with its history becomes essential. This requires both preserving previousl…
cs.CV2026
DiVA: Enabling Interactive Digital Life Simulation via Video Models
Cheng Chen, Hao Ouyang, Qiuyu Wang +11
We present DiVA, a deeply interactive digital life simulator pioneering a new paradigm for long-term, open-ended interactive experiences within digital character worlds. DiVA's arc…
cs.CV2024
Dynamic Typography: Bringing Text to Life via Video Diffusion Prior
Zichen Liu, Yihao Meng, Hao Ouyang +4
Text animation serves as an expressive medium, transforming static communication into dynamic experiences by infusing words with motion to evoke emotions, emphasize meanings, and c…