New framework attributes motion in video generation models

Researchers have developed Motive, a novel gradient-based framework designed to attribute motion in video generation models. This method isolates temporal dynamics from static appearance, enabling efficient and scalable computation of motion-specific influence. Applied to text-to-video models, Motive identifies influential clips that enhance or degrade motion, guiding data curation to improve temporal consistency and physical plausibility. The framework achieved a 74.1% human preference win rate on VBench by improving motion smoothness and dynamic degree. AI

IMPACT This research could lead to more physically plausible and temporally consistent video generation by enabling better data curation for motion dynamics.

RANK_REASON The cluster contains an academic paper detailing a new framework for video generation models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Hugging Face
• VBench
• Xindi Wu

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →