Delighted to be speaking about our recent progress on JEPAs and on the need for more principled solutions that handle data imbalance, noise, multimodality, reasoning, ...! Happening at MICCAI-FOMO26 in 5min! And thank you for having me as keynote today!

New paper advised by Yann LeCun! "H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning" Most world models plan in a single latent space and at one timescale, which makes long-horizon planning expensive and forces one representation to handle both low-level motion and high-level goals. H-JEPA instead stacks JEPA world models across multiple timescales, with higher levels predicting farther into the future. The highest level first figures out roughly where the agent should go, then each lower level turns that into increasingly concrete subgoals until the bottom level outputs actual actions. On Visual AntMaze, this 3-level setup increases success from 18% to 73% while using less planner compute.

[FANCAM] 130724 Yixing di Grandline 4 Yokohama, Jepang (Cr : CHERE_MAMIE_for_Lay) Officially Missing You (cover) - 甜蜜蜜 Sapa meleyot cung☝️☝️🫠 #Grandline4inJP# #LAY# #张艺兴# #레이# #YIXING# #LayZhang# @LAYZHANG_JP @lay_studio @layzhang

[FANCAM] 130724 Yixing di Grandline 4 Yokohama, Jepang (Cr : 补丁76) Love me right (remix) #Grandline4inJP# #LAY# #张艺兴# #레이# #YIXING# #LayZhang# @LAYZHANG_JP @lay_studio @layzhang

Can robotic world models scale predictably like LLMs? RoboJEPA trains JEPA world models from 22M to 8B parameters on data from 12 robot platforms, learning to predict how the world changes under different actions. And they found that prediction error follows a scaling law, with larger models achieving better robotic planning. When scaled enough, capabilities like obstacle avoidance and object manipulation emerge, with successful zero-shot deployment on real robots.

Introducing LeVJEPA 1.5 Large, the first step in scaling our method. It closes the gap to V-JEPA on both image and video benchmarks, trained with 5.6x less compute and over an order of magnitude less data.