Search papers, labs, and topics across Lattice.
3
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.
Achieving robust sim-to-real transfer, this framework allows robots to learn dexterous skills directly from human videos, outperforming traditional methods.
By iteratively challenging LLMs with adaptively generated test cases, this low-code platform co-optimizes code and tests, bypassing the need for manual prompt engineering and boosting reliability in AI-for-Science workflows.
