Cite
Notes
Only stored in your browser.
Attribution
MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation
arXiv 2026
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
arXiv 2025
from 2 papers
Nanqing Liu
Bingyan Liu
Chen Li
Chong Sun
Di wu
Jingyi Liao
Junyi Pan
Linjie Zhong
Nancy F. Chen
Shijie Li