Search papers, labs, and topics across Lattice.
3
0
7
Shrinkage Bias in E2M1 formats could be the hidden culprit behind training instability in LLMs, but uniform grids like E1M2/INT4 offer a robust solution.
Ling-2.6 and Ring-2.6 achieve unprecedented efficiency in agentic intelligence, enabling instant responses and deep reasoning at trillion-parameter scale.
Ditch SwiGLU's quadratic instability: PowLU offers a rational power function that stabilizes LLM pre-training without sacrificing performance.
