AVA-Encoder: Towards Agent-Native Video Representation Learning
Agentic video creation systems remain far from cinematic-grade quality: their underlying models struggle to plan how story, characters, visuals, and sound fit together, and high-quality creation trajectories to learn such planning abilities are scarce. Finished human films embody this knowledge, but in a tightly coupled audiovisual form that agents cannot directly read or manipulate. We propose the Agentic Video Auto-Encoder (AVA-Encoder), which works backward from finished films, turning them into agent-native representations with reconstruction itself as supervision. It encodes a film into a Film Knowledge Graph (Film KG) of structured-text nodes, typed dependency edges, and linked mult...
| Authors | Chuyue Li, Jinpeng Yu, Haozhe Wang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 12 August 2026 |
| Last updated at source | 13 October 2026 |
Popularity, last 7 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Models and datasets referencing this paper
- EurekaTian/RAREDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 23 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.