Search papers, labs, and topics across Lattice.
AXXX, Moscow, Russia, Lomonosov Moscow State University, Moscow, Russia
4
0
4
Persistent memory in EvoMem reduces redundant exploration in evolutionary code search, leading to faster and more effective optimization across multiple tasks.
Modified SINNs achieve superior accuracy in high-dimensional PDEs, outperforming traditional spectral methods and standard PINNs.
Explicit supervision of failed reasoning branches boosts model recovery rates, leading to a dramatic 72.7 percentage point improvement in solving hidden graph tasks.
LLMs struggle with complex theorem proving, often opting for inefficient strategies that highlight a significant gap in their reasoning capabilities.
