2025 Poster "exponential moving average" Papers
3 papers found
Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection
Marc-Antoine Lavoie, Anas Mahmoud, Steven L. Waslander
CVPR 2025posterarXiv:2503.23220
6
citations
Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
Shane Bergsma, Nolan Dey, Gurpreet Gosal et al.
ICLR 2025posterarXiv:2502.15938
22
citations
The AdEMAMix Optimizer: Better, Faster, Older
Matteo Pagliardini, Pierre Ablin, David Grangier
ICLR 2025posterarXiv:2409.03137
23
citations