Hokin Deng
Hi, there! I work at the intersection of human and machine intelligence. I have two convictions on intelligence: one is development, the other is embodiedment.
You could check out my works on the developmental approach to intelligence at Growing AI Like A Child.
Joining MyoLab as a founding member of technical staff, I embark on the journey of building Human-Embodied artificial intelligence.
Previously, I studied philosophy at Johns Hopkins. There, I was mentored and deeply influenced by Michael Williams, Peter Achinstein, and Eckart Förster.
G.Scholar
X
Bluesky
Contact me:
hokind@andrew.cmu.edu
Vision Language Models See What You Want but not What You See
Qingying Gao, Yijiang Li, Haiyun Lyu, Haoran Sun, Dezhi Luo, Hokin Deng
Webpage •
Poster •
Paper •
IntentBench Data
PerspectBench Data
Vision Language Models Know Law of Conservation without Understanding More-or-Less
Dezhi Luo, Haiyun Lyu, Qingying Gao, Haoran Sun, Yijiang Li, Hokin Deng
Webpage •
Poster •
Paper
Probing Mechanical Reasoning in Large Vision Language Models
Haoran Sun, Yijiang Li, Qingying Gao, Haiyun Lyu, Dezhi Luo, Hokin Deng
Webpage •
Poster •
Paper •
Data
Evaluating Multi-modal Language Models Through Concept Hacking
Yijiang Li, Bingyang Wang, Tianwei Zhao, Qingying Gao, Hokin Deng, Dezhi Luo
Poster •
Paper
Probing Perceptual Constancy in Large Vision Language Models
Haoran Sun, Suyang Yu, Yijiang Li, Qingying Gao, Haiyun Lyu, Hokin Deng, Dezhi Luo
Paper •
Data
The Philosophical Foundations of Growing AI Like A Child
Dezhi Luo, Yijiang Li, Hokin Deng
Paper