Search papers, labs, and topics across Lattice.
Xidian University
3
1
7
Reasoning segmentation gets a boost: forcing models to describe what they see before reasoning cuts chain length by 42% and improves accuracy.
Achieve real-time, high-precision GUI navigation with minimal resources by pruning redundant visual tokens *without* retraining.
Forget painstakingly engineering robot behaviors: DreamZero learns directly from video of other robots or even humans, adapting to new tasks and bodies with just minutes of data.
