Valeo fits scaling laws for video diffusion using 5,500 hours of driving footage

abursuc · x · 2026-09-10

VATIX is a valeo.ai research project presented at the ECCV 2026 DriveX workshop: How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models.

Motivation: video generation for autonomous driving can't simply follow web-scale LLM recipes — driving data is expensive, privacy-constrained, and limited in unique coverage, and diffusion models differ from LLMs in training dynamics and scaling behavior. The core question: given a fixed driving dataset, how should compute be allocated to improve generation?

Paper, code, models, and dataset are released, with side-by-side ground-truth vs. generated driving clips.

Original post →

More from Multimodal

Multimodal channel →