Zhenghan Chen, Zekai Shao, Xin Lin, Leting Cheng, Siming Chen · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28416 · open-access PDF
Generasi video berbasis kode menawarkan kontrol yang halus, pengeditan yang ditargetkan, dan penggunaan ulang komponen dibandingkan dengan produksi video langsung. Pendekatan ini membutuhkan model bahasa besar multimodal (MLLM) untuk menerjemahkan persyaratan visual dan waktu menjadi program yang dapat dieksekusi yang menghasilkan video lengkap. Namun, referensi berbasis kode yang ada terutama menargetkan tugas-tugas khusus, meninggalkan penciptaan video lengkap di berbagai kategori kreatif dan modal input tidak cukup dievaluasi.
Machine translation (Meta M2M100); the English original follows.
Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal large language models (MLLMs) to translate visual and temporal requirements into executable programs that produce complete videos. However, existing code-based benchmarks primarily target specialized tasks, leaving complete video creation across diverse creative categories and input modalities insufficiently evaluated. We introduce Code2Video-Compass, a general-purpose benchmark for code-based video generation across text-to-vid
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=2610.28416, 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