Human Intuition
Human intuition, the ability to make rapid, seemingly effortless judgments, is a subject of intense scientific inquiry aiming to understand its mechanisms and replicate its effectiveness in artificial systems. Current research focuses on modeling intuition using techniques like reinforcement learning (e.g., Q-learning variants incorporating belief models), probabilistic graphical models, and transformer-based architectures, often comparing model outputs to human judgments in various tasks (e.g., image captioning, text ranking, causal reasoning). These efforts are significant because they could lead to more robust, explainable AI systems and improved human-AI collaboration in diverse fields, from robotics and investment analysis to healthcare and scientific discovery.
Papers
Haptic-ACT: Bridging Human Intuition with Compliant Robotic Manipulation via Immersive VR
Kelin Li, Shubham M Wagh, Nitish Sharma, Saksham Bhadani, Wei Chen, Chang Liu, Petar Kormushev
Human-like Affective Cognition in Foundation Models
Kanishk Gandhi, Zoe Lynch, Jan-Philipp Fränken, Kayla Patterson, Sharon Wambu, Tobias Gerstenberg, Desmond C. Ong, Noah D. Goodman