PulseAugur
中
实时 08:00:58
English(EN) Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing

Goku 数据集和基准推动指令驱动视频编辑发展 · 跟踪 4 个来源

作者 PulseAugur 编辑部 · [4 个来源] ·

研究人员推出了 Goku，一个用于指令驱动视频编辑的大规模数据集和基准，旨在克服现有数据集仅关注单一任务外观编辑的局限性。Goku 包含 200 万个高质量视频编辑对，支持多任务和结构化操作，如精确的主题移动控制。配套的 Goku-Edit 模型采用多模态大语言模型进行指令理解，并采用双分支设计进行结构和外观编辑。还发布了一个基准 Goku-Bench，包含 1,000 个经人类验证的案例和 7 个新指标，结果显示 Goku-Edit 在指令遵循方面比其他开源模型提高了高达 8%。 AI

影响 提升了指令驱动视频编辑的能力，可能使用户能够进行更复杂和富有创意的用户驱动视频编辑。

排序理由 该集群描述了一个用于视频编辑的新数据集、基准和模型，作为研究论文发布。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

Goku 数据集和基准推动指令驱动视频编辑发展 · 跟踪 4 个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一个用于视频编辑的新数据集、基准和模型，作为研究论文发布。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
57 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [4]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Goku：一个用于指令式视频编辑的百万级通用数据集和基准测试

    A large-scale video editing dataset and model are introduced that support multi-task and structural manipulations through advanced data synthesis and network architectures.

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Goku：一个用于指令式视频编辑的百万级通用数据集和基准测试

    Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios. To bridge this gap, we present Goku, a large-scale dataset featuring 2 million high-quality, instruction-align…

  3. arXiv cs.CV TIER_1 English(EN) · Sen Liang, Cong Wang, Zhentao Yu, Fengbin Guan, Zhengguang Zhou, Teng Hu, Youliang Zhang, Yuan Zhou, Xin Li, Qinglin Lu, Zhibo Chen ·

    Goku：一个用于指令式视频编辑的百万级通用数据集和基准测试

    arXiv:2606.30599v1 Announce Type: new Abstract: Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios. To bridge this gap, we present Goku, a large-scale dataset fea…

  4. arXiv cs.CV TIER_1 English(EN) · Zhibo Chen ·

    Goku：一个用于指令式视频编辑的百万级通用数据集和基准测试

    Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios. To bridge this gap, we present Goku, a large-scale dataset featuring 2 million high-quality, instruction-align…

相关实体

相关话题