Search papers, labs, and topics across Lattice.
5
0
9
7
MoE dLLMs can outperform leading models with significantly fewer training tokens, challenging assumptions about data efficiency in large-scale language models.
DualAlign boosts action quality assessment accuracy by over 21% through innovative multi-modal fusion and adaptive alignment techniques.
A 7B parameter model, guided by a novel RL framework, can now generate multi-page websites that rival the functionality of a 671B parameter model, while surpassing it in visual appeal.
A single model now rivals specialized vision-language models in understanding, while also generating and editing images, thanks to a unified discrete diffusion framework.
LLMs break in two fundamentally different ways when pushed to extreme quantization: either through gradual information loss or sudden functional breakdown of key components.
