RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models

Youngjun Lee, Doyoung Kim, Junhyeok Kang, Jihwan Bang, Hwanjun Song +2 more

2/12/2026

No official code found. Best implementation: xinqi-fan/TT-RAA (10 stars, last commit 2025-08-01).

Semantic Scholar

Code Implementations(1)

xinqi-fan/TT-RAACommunity70%

Official implementation of the paper: "Test-Time Retrieval-Augmented Adaptation for Vision-Language Models" [ICCV 2025]

100Shell, PythonAug 1, 20251 years agoNOASSERTION

Cite this paper

@article{lee2026ratta,
  title  = {RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models},
  author = {Youngjun Lee and Doyoung Kim and Junhyeok Kang and Jihwan Bang and Hwanjun Song and Jae-Gil Lee and Kaist},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:a36829fc16860168a44f0ba001bfc351d635d596},
  journal = {ICLR 2025 2025}
}

RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models

Code Implementations(1)

Cite this paper

Discussion