Search papers, labs, and topics across Lattice.
3
0
8
4
LingBot-VLA 2.0 showcases a remarkable leap in robotic manipulation, achieving strong cross-embodiment performance with enhanced predictive capabilities.
Achieve the same self-consistency with up to 75% less compute by intelligently allocating reasoning trajectories based on question difficulty.
LLM judges are surprisingly susceptible to subtle rubric manipulations that can induce significant preference drift, even while maintaining benchmark performance, creating a stealthy attack surface for biasing model alignment.
