Search papers, labs, and topics across Lattice.
3
3
5
6
ShimGen not only matches but surpasses manually-designed protocols in consistency, revealing critical performance gains in heterogeneous memory systems.
Switching between autoregressive and diffusion modes allows Nemotron-Labs-Diffusion to achieve unprecedented throughput and efficiency in language modeling.
Ditch the slow lane: $R^2$-dLLM turbocharges diffusion language models by slashing decoding steps by up to 75% without sacrificing quality.
