LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks.
Model predictive heuristic control: Applications to industial processes.Automatica, 14(5):413–428, 1978
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks.