Qiuping Deng

Evaluator quality for robotic policies hinges more on long-horizon consistency than on short-term visual fidelity, reshaping our approach to world model design.

Treating raw visual images as action representations revolutionizes embodied control, outperforming traditional methods in accuracy and generalization.

Robots can now better assemble boxes in the real world thanks to a video-generative value model that anticipates future states, moving beyond static snapshots for more reliable task progress assessment.

Robots can now plan 9x faster and achieve significantly higher success rates by decoupling action prediction from video generation in World-Action Models.