activity
20192026
most citedAn Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection

29 citations · 30 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful

Martin Marek, Sanae Lotfi, Aditya Somasundaram +2

Conventional wisdom dictates that small batch sizes make language model pretraining and fine-tuning unstable, motivating gradient accumulation, which trades off the number of optim…