Tag
Fast-LeWM accelerates visual planning by replacing autoregressive rollout with parallel action-prefix prediction, reducing computational costs and latency accumulation during long-horizon predictions.
This paper audits Joint-embedding predictive architectures (JEPA) for LLM fine-tuning on a natural-language-to-regex task, testing twenty-two auxiliary objectives. The results show that hidden-state representation improvements are only weakly coupled to decoded-task accuracy, with no auxiliary surviving family-wise correction.