CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
Paper • 2604.19741 • Published • 11
Nora
nogully
·
AI & ML interests
multimodal, multilingual, NLP + interpretability research
Recent Activity
liked a Space 1 day ago
clem/macron-chat liked a Space 1 day ago
taesiri/ai-deadlines upvoted a paper 1 day ago
CityRAG: Stepping Into a City via Spatially-Grounded Video GenerationOrganizations
None yet