Search papers, labs, and topics across Lattice.
Tianjin University
4
0
6
WarpSAC achieves up to a 96.4% success rate in complex tasks by dynamically adjusting its learning stabilizers based on data availability.
Hy-Embodied-VLM-1.0 outperforms its predecessor by 8.4% while activating only a fraction of the parameters, redefining efficiency in embodied agents.
Achieving state-of-the-art performance with just 8 billion parameters, Embodied-R1.5 redefines the capabilities of embodied models in complex physical tasks.
Forget robotics pre-training: ActionCodec, a new action tokenizer designed with information-theoretic principles, achieves state-of-the-art VLA performance on LIBERO.
