3 papers
cs.LG2026
Does Learning Protein Folding Generalize to Broader Reasoning?
Yong Liu, Zhanpeng Shi, Yizhou Dang +4
Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protein folding is a natural testbed…
cs.AI2026
Where World Models Break: Natural-Input Failure Discovery
Zhanpeng Shi, Zi Liang, Rong Feng +3
World models predict action-conditioned futures and serve as critical internal simulators for downstream planning and control. However, catastrophic prediction failures of world mo…
cs.AI2026
Tactile: Giving Computer-Using Agents Hands and Feet
Yong Liu, Zhenyi Zhong, Zhanpeng Shi
Computer-use agents are becoming capable software operators, but their interface to desktop applications is still often a brittle motor layer: they look at screenshots, predict coo…