Simignore improves multimodal LLM complex question answering on ScienceQA by masking image tokens whose embeddings have low cosine similarity to the text prompt.
Title resolution pending
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
-
Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation
Simignore improves multimodal LLM complex question answering on ScienceQA by masking image tokens whose embeddings have low cosine similarity to the text prompt.