arxiv:2512.04356
Kai-Po Chang PRO
kaipochang0810
ยท
AI & ML interests
Truthworthy Vision-language Large Models
Vision-language(-action) World Models
Recent Activity
authored
a paper
21 days ago
Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
Organizations
None yet