← Back to literature explorer
Weakly Supervised From survey PDF — verify links

CALLM

CALLM — LLM Knowledge Enhancement

IPTA · 2024

Survey summary

CALLM cascades a 3D deep autoencoder with a large video-language model: the autoencoder's binary classification flags abnormality and triggers a follow-up query to the LVLM for detailed explanation, using weakly supervised caption extraction and pseudo-instruction injection to improve performance.

Weakly Supervised

Weakly SupervisedLLM Knowledge Enhancement
Weakly Supervised3D autoencoderVideo-LLaMAPseudo-instruction