TTL dynamically learns OOD textual semantics from unlabeled test streams via prompt updates, purification, and a knowledge bank to improve detection performance in pretrained VLMs.
Improving information retention in large scale online continual learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Models
TTL dynamically learns OOD textual semantics from unlabeled test streams via prompt updates, purification, and a knowledge bank to improve detection performance in pretrained VLMs.