A joint team from NVIDIA, MIT, Princeton, and others took an ICML 2026 Outstanding Paper Honorable Mention with Motive. Motive is the first "motion attribution" framework for video generation models, based on optical-flow masks and gradient attribution, and using only 10% of the data, it lifts Wan2.1-T2V-1.3B's VBench Dynamic Degree by 8.0 points, and Wan2.2-TI2V-5B by 6.3 points, with a 74.1% win rate in 850 blind evaluations from 17 human evaluators.