HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models
Paper
•
2310.14566
•
Published
•
27
LZX
zli12321
AI & ML interests
go with the flow
Recent Activity
upvoted
a
paper
about 1 month ago
VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal
Reasoning
upvoted
a
paper
about 1 month ago
CLUE: Non-parametric Verification from Experience via Hidden-State
Clustering
upvoted
a
paper
about 2 months ago
Evolving Language Models without Labels: Majority Drives Selection,
Novelty Promotes Variation
Organizations
authored
a
paper
about 2 years ago