AI

SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 09/10/2026, 06:18:24 UTC.

Briefings

SPW-Nav is a language-guided panoramic world model that generates 2K 360-degree video in real time from a single panorama by interpreting movement instructions. It outperforms existing generators in camera-following accuracy and supports on-the-fly instruction switching, with spherical rotation decoupling and pose-aligned conditioning ensuring stable long-term generation.

Key points

• SPW-Nav generates 2K 360-degree video in real time from a single panorama by interpreting movement instructions.
• SPW-Nav outperforms prior panoramic generators in camera-following accuracy and supports on-the-fly instruction switching.

Context

Language-guided panoramic video generation benefits interactive 3D scene exploration, virtual reality experiences, and embodied agent training. Existing generators follow predefined trajectories, while interactive world models act through low-level actions in perspective views.

Limitations

Evidence covers only the SPW-NavSet dataset with verified instructions. No performance metrics or user impact data are provided. Results are based on internal model evaluation rather than external validation.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 14/11/2026, 22:18:50 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeicvb36efxqnibaj47kas5c2yz63fxofn5bjhzg27ygbgxg67qjk2q