Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
Paper
•
2512.04356
•
Published
•
10
•
3
Kai-Po Chang
kaipochang0810
AI & ML interests
Truthworthy Vision-language Large Models
Vision-language(-action) World Models
Recent Activity
View all activity
Organizations
None yet
commented
2
papers
about 2 months ago