๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

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 โ€˜26).
๊ฐ€์ž… October 2026
79 ํŒ”๋กœ์ž‰ ์ค‘    65 ํŒฌ
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... ๐Ÿงต๐Ÿ‘‡
๋” ๋ณด๊ธฐ