Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
3
0
5
LLMs can now achieve 66x storage reduction and 1.86x speedup at 128K context by internalizing memory, not just retrieving it.
Dense process supervision can transform RL training by providing step-level rewards that enhance credit assignment, leading to superior performance in complex reasoning tasks.
The minimax risk in deep Gaussian regression exhibits a surprising quadratic dependence on depth, challenging conventional assumptions about model capacity.