Multimodality · 2025
Wan: Open and Advanced Large-Scale Video Generative Models
An open-weight video foundation model suite that topped the VBench leaderboard and became a widely adopted base for the open text-to-video ecosystem.
Editorial record
Plain-language summary
An open-weight video foundation model suite that topped the VBench leaderboard and became a widely adopted base for the open text-to-video ecosystem.
Knowledge graph
Relationships
Descendants
Depends onEvidence: Strongly supported
Attention Is All You Need
Builds on the multimodal lineage in the archive
freshness sweep 2026
Source record
Provenance
- Record ID
- P-623
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2503.20314
- arXiv:2503.20314
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.