GRACE improves ID accuracy by 10.8% and adversarial accuracy by 13.5% on ImageNet-tuned CLIP while holding OOD accuracy near the zero-shot baseline.
LoRA: Low-rank adaptation of large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
GRACE improves ID accuracy by 10.8% and adversarial accuracy by 13.5% on ImageNet-tuned CLIP while holding OOD accuracy near the zero-shot baseline.