LoRA-TTT improves CLIP's zero-shot accuracy under distribution shift by test-time training only low-rank adapters in the image encoder, using entropy and masked-class-token consistency losses.
Tinytl: Reduce memory, not parameters for efficient on-device learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models
LoRA-TTT improves CLIP's zero-shot accuracy under distribution shift by test-time training only low-rank adapters in the image encoder, using entropy and masked-class-token consistency losses.