Search papers, labs, and topics across Lattice.
5
0
6
1
Quoting evidence directly from documents boosts evidence recall by up to 39 points while halving hallucination rates, challenging the reliance on coordinate-based methods.
Real-time 3D reconstruction can now achieve state-of-the-art accuracy and rendering quality thanks to a novel integration of global optimization and color residual learning.
Many VLA models fail to translate semantic understanding into accurate action selection, often performing at near-random levels despite successful grasping.
Software vulnerability detection gets a serious upgrade: aligning code with developer comments boosts F1 scores by up to 27% compared to traditional code-only methods.
Transforming human motion into structured language allows LLMs to achieve unprecedented accuracy in motion understanding without the constraints of traditional encoding methods.
