{
  "id": 18328,
  "url": "https://arxiv.org/abs/2608.08553v1",
  "title": "MotionCraft: Latent World Modeling with Sparse Attention for Visual Upscaling",
  "summary": "Video super-resolution (VSR) aims to recover high-fidelity high-resolution videos from low-resolution inputs and is central to applications ranging from mobile capture to streaming and archival restoration. Existing approaches trade off among local-detail fidelity, long-range spatio-temporal modeling, perceptual realism, and efficiency: convolutional alignment techniques preserve local structure but suffer when motion is large or degradations are complex; transformer-based methods capture long-r",
  "authors": "Rong Fu, Chunlei Meng, Yangchen Zeng, Xiaowen Ma, Yongtai Liu, Wangyu Wu et al.",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-09T07:54:43.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18328",
  "original_url": "https://arxiv.org/abs/2608.08553v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}