Search papers, labs, and topics across Lattice.
3
0
8
Scaling test-time compute can dramatically improve the success rate of robot imitation learning, achieving up to 95% on complex manipulation tasks.
LLMs that ace medical exams still fumble basic clinical judgment, prematurely deciding cases or abstaining unnecessarily when information is incomplete, revealing a critical gap in their real-world applicability.
Predict transformer training failures *before* you even start training, with 99.5% accuracy, using just a single forward pass.
