Loading
Vision-language models struggle with test-time transduction. This model uses dynamic shrinkage to improve performance. Realistic evaluations are still a challenge
“arXiv:2607.15851v1 Announce Type: cross Abstract: A range of methods aim to enhance the performance of vision-language models (VLMs) at test time. Among them, transduction has emerged as a promising paradigm due to its strong compatibility …”
Read the source →STATUS
ACTIVE
CATEGORY
Models
EVIDENCE
Not yet assessed
ENTITY
Von Mises-Fisher Mixture Model, vision-language models
DECISION
Automated · no editorial override
LAST OBSERVED
Aug 6, 2026