A fine-tuned LLaVA model, trained with preference optimization on 800 emotional image-QA examples, beats GPT-4o on a new empathy-focused benchmark for visual impairment assistance.
A multi-world approach to question answering about real-world scenes based on uncertain input
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
background 1representative citing papers
citing papers explorer
-
EmoAssist: Emotional Assistant for Visual Impairment Community
A fine-tuned LLaVA model, trained with preference optimization on 800 emotional image-QA examples, beats GPT-4o on a new empathy-focused benchmark for visual impairment assistance.