Search papers, labs, and topics across Lattice.
3
0
6
4
AsyncWebRL achieves a staggering 2.9脳 increase in training throughput while setting a new state-of-the-art performance for web agents on challenging tasks.
The hardest AI tasks remain largely unsolved, with current models achieving only a 2.6% success rate on economically valuable workflows.
Diffusion language models can achieve faster convergence and improved accuracy simply by swapping token-choice routing for expert-choice routing, and further benefit from allocating more compute to early denoising steps.
