David Grangier

3
Papers
26
Total Citations

Papers (3)

The AdEMAMix Optimizer: Better, Faster, Older

ICLR 2025
23
citations

No Need to Talk: Asynchronous Mixture of Language Models

ICLR 2025
3
citations

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging

ICML 2025
0
citations