This paper presents Long Context Tuning (LCT) to enhance video generation models, enabling coherent multi-shot scenes and improving visual content creation through expanded context and efficient generation techniques.

https://arxiv.org/abs//2503.10589

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers