Point Tracking Improves World Action Models
- Published
- Source
- arXiv
- Paper number
- 234
- Field
- Robotics
- arXiv ID
- 2605.23856
Key points
- Register token r is a learnable token that helps global information processing.
- Models that use only latent representations lacked the precision needed for long-horizon action, and they failed when visual cues were subtle.
- Models that use only tracks lacked the semantic grounding needed to identify which object to interact with.
Paper links
External research summaries. These are not HDATF publications or measured product results.