Search papers, labs, and topics across Lattice.
Department of Artificial Intelligence, Sungkyunkwan University
2
0
5
Forget passively curated videos: VGenST-Bench actively synthesizes diverse, controlled video scenarios to expose the spatio-temporal reasoning gaps in your MLLMs.
Forget siloed robots: MLLMs can orchestrate sensing, communication, and computation across robot networks to achieve superhuman task performance.
