Han-Jun Ko

@han-jun-ko · 1 works

Researches vision-language models and their generalization in interactive physical reasoning tasks.

Recent posts by Han-Jun Ko

• Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment - Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated… · Paper · arxiv.org

Topics Han-Jun Ko posts about

• VLM on Instagram - 1 post · Best VLM creators