Search papers, labs, and topics across Lattice.
2
0
5
4
Robots can now think (and act) much faster: ElegantVLA intelligently allocates compute within Vision-Language-Action models, leading to up to 3.77x speedups without sacrificing performance.
LLMs can achieve a "free lunch" in reasoning tasks, simultaneously improving accuracy and reducing token usage by simply training them to solve multiple problems in parallel.
