Search papers, labs, and topics across Lattice.
Zhishu Liu and Kaishen Yuan contributed equally to this work.Corresponding authors: Zitong Yu and Hui Ma.Z. Liu, B. Zhao, H. Ma, and Z. Yu are with Great Bay University, Dongguan, China.H. Ma is also with Shenzhen International Graduate School, Tsinghua University, Shenzhen, China.K. Yuan is with The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
Tsinghua AI2
0
5
Stop predicting the future, start predicting *change*: $Δ$VLA guides robotic action by modeling how world knowledge *varies* under actions, not by forecasting absolute future states.
LLMs can significantly boost micro-expression recognition by reasoning about subtle facial muscle movements when guided by structured visual and relational prompts.
