Denoising autoencoder pretraining on corrupted visual embeddings yields more robust Med-VQA performance on SLAKE and PathVQA while using LoRA for efficient LLM adaptation.
Title resolution pending
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
-
Noise-Aware Visual Representation Learning for Medical Visual Question Answering
Denoising autoencoder pretraining on corrupted visual embeddings yields more robust Med-VQA performance on SLAKE and PathVQA while using LoRA for efficient LLM adaptation.