CPT creates cluster-invariant spaces from pre-trained VLM semantics and applies neural collapse losses to boost long-tail performance and unseen-class generalization in prompt tuning.
Scaling up visual and vision-language representation learning with noisy text supervision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
SpeciaRL applies a dynamic verifier-based reward in reinforcement learning to steer reasoning LMMs toward correct and specific predictions on fine-grained open-world image classification tasks.
citing papers explorer
-
Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
CPT creates cluster-invariant spaces from pre-trained VLM semantics and applies neural collapse losses to boost long-tail performance and unseen-class generalization in prompt tuning.
-
Specificity-aware reinforcement learning for fine-grained open-world classification
SpeciaRL applies a dynamic verifier-based reward in reinforcement learning to steer reasoning LMMs toward correct and specific predictions on fine-grained open-world image classification tasks.