← Search

Brody Huval

2 accepted papers

2025

Cut Your Losses in Large-Vocabulary Language Models

ICLR 2025oral

As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entropy in the loss computation. Cross-entropy builds up a logit matrix with entries for each pair of input tokens and vocabu…

2025

Robust Autonomy Emerges from Self-Play

ICML 2025poster

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale -- 1.6 billion km of driving…

Cited by 4SourcePDFScholar