←Back to NewsAI News/RoboticspaperRoboticsVideoYann LeCun's AD-E2E-JEPA Plans Driving Trajectories 100x Faster Without Policy TrainingA new JEPA world model drives without a trained policy, hitting goals 20 meters out with a 100x inference speedup over prior latent planners.SourceAlphaSignalPublishedSep 28, 2026, 1:22 AMAuthorAlphaSignal NewsroomRead1 min readA new JEPA world model drives without a trained policy, hitting goals 20 meters out with a 100x inference speedup over prior latent planners.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsOdyssey · newsOdyssey's Agora-2 Lets 20 Players Share One AI-Generated WorldOdyssey · newsOdyssey Builds One AI Backbone to Control Robots, Cars, Drones, and GamesUnitree · newsUnitree's UnifoLM-X2-1.0 Lets Humanoid Robots Fight With No Human Control
