Pretraining Latent Information Feedback Transformers with Teacher Supervision
LIFT pretrains Transformers to recycle latent state and beats token-matched baselines from 135M to 1B.
52
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 28, 2026
- Last mentionedSep 29, 2026
Timeline
2 articles · newest firstLIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation
LIFT controls future-frame layout in image-to-video generation under large camera viewpoint changes.
38
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.