Kwang Moo Yi (@kwangmoo_yi)
2025-12-04 | ❤️ 64 | 🔁 6
Xiao et al., “Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation”
Fine-tune a video model to generate videos based on context, solving object grounding and scene navigation. Another one in the trend of “let’s generate solution videos” https://x.com/kwangmoo_yi/status/1996687925569007985/video/1
🔗 원본 링크
미디어
