Get started
Author

Gavia Gray

Observed name: Gray, Gavia
Observed institution: Cerebras Systems (United States)
OpenAlex ID: A5144871086
Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference
2026 · Elhoushi, Mostafa, Pretko, Alex, et al. · arXiv (Cornell University)
PDF
Power Lines: Scaling laws for weight decay and batch size in LLM pre-training
2025 · Shane Bergsma, Nolan Dey, et al. · neural information processing systems
PDF
Works count: 2
Citation count:
H-index:
I10-index:
Year
Topic
Type