注册并分享邀请链接,可获得视频播放与邀请奖励。

Romina Yalovetzky
@RominaYalov
Physicist bringing ideas from physics to computation: quantum & AI/ML. 10+ yrs in tech. Lead Applied Researcher @JPMorgan. MSc CS @NYUCourant (Fall ‘26).
加入 October 2026
79 正在关注    65 粉丝
Can a JEPA world model provably avoid contraction and merging of latent states over long rollouts? Unconstrained autoregressive predictors may contract the latent distribution. Our Symplectic Hamiltonian JEPA (LeHami) replaces the predictor with an action-conditioned Hamiltonian flow over a latent state (q, p), integrated with an exactly symplectic leapfrog step. Volume is preserved at every rollout step, independently of the learned parameters or action sequence. With @randall_balestriero @ylecun Paper: Website: Code: 1/6... 🧵👇
显示更多
0
4
187
18
转发到社区