arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Computer Vision · 会议 · Computer Vision

2026-05-22 至 2026-05-22 共收录 1
2510.05094 2026-05-22 cs.CV

VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

VChain:用于视频生成中推理的视觉思维链

Ziqi Huang, Ning Yu, Gordon Chen, Haonan Qiu, Paul Debevec, Ziwei Liu

机构 * eyeline-labs(Eyeline Labs)

AI总结 本文提出VChain,一种在视频生成中引入多模态模型视觉推理信号的新型推理时间视觉思维链框架,通过生成关键帧来指导预训练视频生成器的稀疏推理时间视觉状态适应,从而提升视频生成质量。

Comments ACL 2026 (Findings Paper), ICCV 2025 Workshop Outstanding Paper Award, Project page: https://eyeline-labs.github.io/VChain

详情

展开后加载摘要…

URL PDF HTML 收藏