Search papers, labs, and topics across Lattice.
5
0
10
8
DOPD reveals that intelligently routing supervision based on advantage gaps can significantly enhance capability transfer in distillation, outperforming conventional methods.
IF-Beta allows student models to achieve superior performance with significantly less data and compute, challenging the traditional reliance on full datasets in knowledge distillation.
Rethinking image segmentation, Rea2Seg achieves superior mask generation by combining candidate discovery with sophisticated reasoning over multimodal queries.
LLMs can now build playable games from scratch, thanks to a new framework that teaches them to scaffold stable architectures and systematically debug integration errors, not just patch syntax.
Language models are increasingly doing their real work in the "invisible" latent space, not the tokens we see.
