Search papers, labs, and topics across Lattice.
5
0
6
4
Achieving up to 88x efficiency gains, Taylor-Calibrate transforms the way we initialize hybrid linear attention models, drastically reducing the training burden.
Diffusion language models can now match autoregressive quality, thanks to a clever trick that forces them to agree with themselves.
Verifier-free evolution can now match or exceed the performance of verifier-based methods, while slashing API costs by 3x and boosting throughput by 10x, thanks to a clever model orchestration strategy.
Forget SVD: CARE aligns low-rank attention approximations with input activations, boosting accuracy up to 1.7x and slashing perplexity by 215x when converting models to multi-head latent attention.
Models are substantially better at pairwise self-verification than independent scoring, unlocking a more efficient and accurate approach to test-time scaling for complex reasoning.
