Search papers, labs, and topics across Lattice.
4
0
7
Ling-2.6 and Ring-2.6 achieve unprecedented efficiency in agentic intelligence, enabling instant responses and deep reasoning at trillion-parameter scale.
LLMs can now forecast time series data with greater accuracy and interpretability by fusing their reasoning capabilities with traditional time series models in a novel agentic framework.
HeadRank achieves a remarkable 43-percentage-point improvement in selecting relevant documents from the middle-context zone, revolutionizing passage reranking efficiency.
LLM judges inflate math proof scores by up to 0.36 points, revealing a significant alignment gap with human experts and a reasoning breakdown in discrete domains.
