Taming LLMs by Scaling Learning Rates with Gradient Grouping
Paper
•
2506.01049
•
Published
•
38
Efficient AI (Optimization)
-
-
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Paper • 2402.09240 • Published • 4 -
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 35 -
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Paper • 2209.04851 • Published • 3