Shengqiong Wu, Meng Luo, Bobo Li, Ziwei Liu, Shuicheng Yan, Ming-Hsuan Yang, Philip Torr, Hao Fei · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31668 · open-access PDF
Model dasar video telah berkembang pesat dalam memahami dan menghasilkan urutan visual, sementara model dunia video berusaha menangkap dinamika dasar dunia yang mereka gambarkan. Terlepas dari tujuan mereka yang berbeda, keduanya berkaitan dengan hubungan antara pengamatan video dan dunia yang sedang berkembang. Survei ini mengadopsi pemodelan dunia sebagai lensa yang menyatukan untuk mengeksplorasi perkembangan ini. Menonton video yang diamati sebagai proyeksi parsial, kerugian, dan secara berurutan dari dunia temporal latent, kami mengatur literatur di sekitar empat operasi komplementer: membaca mengacu pada sifat-sifat dunia dari
Machine translation (Meta M2M100); the English original follows.
Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they depict. Despite their different objectives, both concern the relationship between video observations and an evolving world. This survey adopts world modeling as a unifying lens for examining these developments. Viewing an observed video as a partial, lossy, and temporally ordered projection of a latent temporal world, we organize the literature around four complementary operations: reading infers world properties from
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31668, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange