Search papers, labs, and topics across Lattice.
2
0
4
Speculative decoding drafters no longer need to be trained from scratch per model: target-agnostic pretraining on pruned small LMs produces a single, reusable backbone that outperforms bespoke drafters by up to 22.7% across completely different target architectures.
Diffusion language models can now match autoregressive quality, thanks to a clever trick that forces them to agree with themselves.
