Paper characterizes JEPA feature selection as predictive closure
Unpredictable features can still be encoded when they help predict other features.
3 stories, newest first · one card per story
Unpredictable features can still be encoded when they help predict other features.
Researchers introduce JEPA-Anything, a domain-agnostic predictive world-modeling framework using orthogonal predictive factorization, validated across seven domains including biology and weather.
Researchers present JEPA-Anything, a domain-agnostic world-modeling framework improving prediction across vision, biology, control, molecular dynamics, and weather.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views