Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper
•
2601.19895
•
Published
•
23
LLM
-
-
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
Paper • 2601.17367 • Published • 33 -
Small-scale proxies for large-scale Transformer training instabilities
Paper • 2309.14322 • Published • 21 -
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
Paper • 2602.00747 • Published • 8