ReasonCLIP-58M applies continual pretraining with visually grounded reasoning captions on 58M examples to improve CLIP-style models on commonsense and compositional reasoning tasks.
arXiv preprint arXiv:2602.23351 (2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
ReasonCLIP-58M applies continual pretraining with visually grounded reasoning captions on 58M examples to improve CLIP-style models on commonsense and compositional reasoning tasks.