Frozen LLM text encoders, combined with multi-prompt hidden-state extraction and cached embeddings, make CLIP-style pre-training data-efficient, long-context aware, and multilingual.
Language models are few-shot learners
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training
Frozen LLM text encoders, combined with multi-prompt hidden-state extraction and cached embeddings, make CLIP-style pre-training data-efficient, long-context aware, and multilingual.