# ScaleNav: Internet Video Pretraining for Language-Conditioned Local Navigation

- Source: HuggingFace Daily Papers
- Published: 2026-10-19T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/om0p85prd9eg7y9doh4f0xgbf
- Original: https://huggingface.co/papers/2610.25690

## Summary

ScaleNav proposes a unified world-action framework that achieves language-conditioned local navigation through three-stage training: first, instruction-conditioned video pretraining on internet first-person videos to learn how observations evolve as the camera approaches a target; then, aligning predicted executable action chunks using action-labeled simulation data; and finally, jointly fine-tuning all trainable components.