Search papers, labs, and topics across Lattice.
3
0
5
Ego-centric video scaling saturates agent modeling long before object interaction fidelity, revealing a fundamental bottleneck in current world model training paradigms.
Achieving 19 times lower inference latency than diffusion models, UniGen-AR redefines the efficiency of unified visual generation.
By enabling robots to learn from synthesized data in novel contexts without additional motion data, RoboDream transforms the landscape of robot learning efficiency.
