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

Lukas Kuhn
@lukaskuhn77
AI Researcher @DKFZ Teaching models to imagine the future
๊ฐ€์ž… February 2026
83 ํŒ”๋กœ์ž‰ ์ค‘    444 ํŒฌ
A new Pareto frontier in video pretraining. Excited to introduce LeVJEPA ๐Ÿ”ฅ: a stable, efficient end-to-end pretraining method that matches V-JEPA 2 at up to 20x less pretraining compute! No target encoder, no masked prediction, no stop-gradient or teacher-student schedule. One encoder, trained with a single objective. ๐Ÿงต
๋” ๋ณด๊ธฐ