Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing

First seen · 7/1/2026, 12:00 PMLatest activity · 7/1/2026, 12:00 PM

The paper introduces Goku, a dataset of 2 million high-quality, instruction-aligned video editing pairs covering appearance edits as well as multi-task and structural manipulations such as precise subject-motion control. It also presents Goku-Edit, which uses an MLLM text encoder and a decoupled dual-branch architecture with a dedicated mask branch, plus Goku-Bench, a benchmark containing 1,000 human-verified test cases and seven editing-specific metrics. The authors report up to an 8% instruction-following improvement over other open-source models on Goku-Bench.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers7/1, 12:00 PMnot independentRepresentative
    Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing