3 papers
cs.RO2026
PRISM: PRior-guided Imagination Sampling in world Models
Yuhai Wang, Jiawei Xia, Rongxuan Zhou +4
A learned world model provides a powerful physical intuition for evaluating future states. But its effectiveness in continuous control also depends critically on how candidate acti…
cs.AI2026
Some Large Language Models Exhibit Consistent Risk Attitudes
Bowen Sun, Rui Min, Yuxi Wang +3
As artificial intelligence systems are deployed in open-ended, high-stakes settings, a critical dimension remains unmeasured: how perceived risk is translated into action. We test…
cs.AI2025
AI Generations: From AI 1.0 to AI 4.0
Jiahao Wu, Hengxu You, Jing Du
This paper proposes that Artificial Intelligence (AI) progresses through several overlapping generations: AI 1.0 (Information AI), AI 2.0 (Agentic AI), AI 3.0 (Physical AI), and no…