Search papers, labs, and topics across Lattice.
Ant Group
5
0
6
An optimal knowledge distribution can significantly enhance LLM knowledge boundaries, outperforming traditional synthesis methods across multiple benchmarks.
Ling-2.6 and Ring-2.6 achieve unprecedented efficiency in agentic intelligence, enabling instant responses and deep reasoning at trillion-parameter scale.
Unsupervised skill discovery can boost data-analytic agent performance by over 30% without the need for labeled data.
CRAFTQA's ability to dynamically generate custom code functions allows it to tackle complex reasoning tasks that traditional methods cannot handle.
SkillAdaptor achieves targeted skill updates that enhance LLM performance by over 1.5 points on key benchmarks, revolutionizing how agents adapt to failures in real-time.
