Fixing the visual encoder in multilingual CLIP isolates text-branch deficits as the cause of lower visual grounding performance for low-resource languages, with model scaling widening some gaps but not others.
The use of ranks to avoid the assumption of normality implicit in the analysis of variance
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
method 2polarities
use method 2representative citing papers
PCA-Triage adaptively sets sensor sampling rates from incremental PCA loadings to meet bandwidth limits while preserving downstream inference F1 scores close to full-data performance.
A leakage-safe similarity gate and spatial queue-regret decomposition reduce mean passenger wait times to 82.3 seconds in New York City ride-hailing simulations by linking demand-field error directly to wait via queueing and allocator sensitivities.
citing papers explorer
-
Language-Conditioned Visual Grounding with CLIP Multilingual
Fixing the visual encoder in multilingual CLIP isolates text-branch deficits as the cause of lower visual grounding performance for low-resource languages, with model scaling widening some gaps but not others.
-
PCA-Driven Adaptive Sensor Triage for Edge AI Inference
PCA-Triage adaptively sets sensor sampling rates from incremental PCA loadings to meet bandwidth limits while preserving downstream inference F1 scores close to full-data performance.
-
Regime-Calibrated Fleet Repositioning with a Spatial Queue-Regret Decomposition
A leakage-safe similarity gate and spatial queue-regret decomposition reduce mean passenger wait times to 82.3 seconds in New York City ride-hailing simulations by linking demand-field error directly to wait via queueing and allocator sensitivities.