Search papers, labs, and topics across Lattice.
2
24
3
10
Empirically, EPIG reduces gradient MSE in cloned-state control, winning in all nine dense continuous-control environments of a 13-environment sweep and recovering the reference gradient direction near-perfectly, and it improves frozen-LLM gradient calibration relative to entropy branching.
LLMs that excel at math don't necessarily make good math tutors, revealing a surprising trade-off between subject matter expertise and pedagogical skill.
