A LoRA fine-tune of VideoGPT+ on VIST produces strong reference-free metric scores for visual storytelling, but the state-of-the-art claim is undercut by weak baselines and test-set selection.
Diverse and rel- evant visual storytelling with scene graph embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?
A LoRA fine-tune of VideoGPT+ on VIST produces strong reference-free metric scores for visual storytelling, but the state-of-the-art claim is undercut by weak baselines and test-set selection.