GRPO-TTA reformulates test-time adaptation for vision-language models as group-wise policy optimization via top-K sampling from CLIP distributions and alignment/dispersion rewards to tune the visual encoder.
Cliptta: Robust contrastive vision-language test-time adaptation.arXiv preprint arXiv:2507.14312
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning
GRPO-TTA reformulates test-time adaptation for vision-language models as group-wise policy optimization via top-K sampling from CLIP distributions and alignment/dispersion rewards to tune the visual encoder.
- Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs