JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Classical vision-based methods outperform deep learning in accuracy and fairness for depression detection in two clinical contexts, with limited cross-context generalization suggesting context-specific cues.
citing papers explorer
-
Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.
-
Context Matters: Vision-Based Depression Detection Comparing Classical and Deep Approaches
Classical vision-based methods outperform deep learning in accuracy and fairness for depression detection in two clinical contexts, with limited cross-context generalization suggesting context-specific cues.