Search papers, labs, and topics across Lattice.
RND NLP
6
0
8
Recursive reasoning models achieve state-of-the-art algorithmic performance and OOD generalization with a simple optimization recipe, decoupling architectural complexity from recurrent state stabilization.
The proposed greedy algorithm with alternating updates guarantees the four-peak distribution required for stable 2-bit clustering of each factor and admits closed-form initialization of cluster centers, removing the multi-restart k-means bottleneck of prior work.
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.
